Authors: David Zagardo
Abstract: Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high, crippling your model's utility, or too low, compromising privacy. The dreaded realization hits: you must start the lengthy training process from scratch. But what if you could avoid this retraining nightmare? In this study, we introduce a groundbreaking approach (to our knowledge) that applies differential privacy noise to the model's weights after training. We offer a comprehensive mathematical proof for this novel approach's privacy bounds, use formal methods to validate its privacy guarantees, and empirically evaluate its effectiveness using membership inference attacks and performance evaluations. This method allows for a single training run, followed by post-hoc noise adjustments to achieve optimal privacy-utility trade-offs. We compare this novel fine-tuned model (DP-Weights model) to a traditional DP-SGD model, demonstrating that our approach yields statistically similar performance and privacy guarantees. Our results validate the efficacy of post-training noise application, promising significant time savings and flexibility in fine-tuning differential privacy parameters, making it a practical alternative for deploying differentially private models in real-world scenarios.
Authors: Tommaso Baldi (Fermilab, University of Pisa), Javier Campos (Fermilab), Ben Hawks (Fermilab), Jennifer Ngadiuba (Fermilab), Nhan Tran (Fermilab), Daniel Diaz (UC San Diego), Javier Duarte (UC San Diego), Ryan Kastner (UC San Diego), Andres Meza (UC San Diego), Melissa Quinnan (UC San Diego), Olivia Weng (UC San Diego), Caleb Geniesse (UC Berkeley/LBNL/ICSI), Amir Gholami (UC Berkeley/LBNL/ICSI), Michael W. Mahoney (UC Berkeley/LBNL/ICSI), Vladimir Loncar (MIT), Philip Harris (MIT), Joshua Agar (Drexel University), Shuyu Qin (Drexel University)
Abstract: Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling ultra-fine-grained model inspection for efficient fault tolerance. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements in extreme experimental environments. We study metrics for developing robust algorithms, present preliminary results and mitigation strategies, and conclude with an outlook of these and future directions of research towards the longer-term goal of developing autonomous scientific experimentation methods for accelerated scientific discovery.
Authors: Bradley Burega, John D. Martin, Luke Kapeluck, Michael Bowling
Abstract: We study how a Reinforcement Learning (RL) system can remain sample-efficient when learning from an imperfect model of the environment. This is particularly challenging when the learning system is resource-constrained and in continual settings, where the environment dynamics change. To address these challenges, our paper introduces an online, meta-gradient algorithm that tunes a probability with which states are queried during Dyna-style planning. Our study compares the aggregate, empirical performance of this meta-gradient method to baselines that employ conventional sampling strategies. Results indicate that our method improves efficiency of the planning process, which, as a consequence, improves the sample-efficiency of the overall learning process. On the whole, we observe that our meta-learned solutions avoid several pathologies of conventional planning approaches, such as sampling inaccurate transitions and those that stall credit assignment. We believe these findings could prove useful, in future work, for designing model-based RL systems at scale.
Authors: Vitaly Feldman, Audra McMillan, Satchit Sivakumar, Kunal Talwar
Abstract: Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating population densities in a geographic region, a small Wasserstein distance means that the estimate is able to capture roughly where the population mass is. In this work we study differentially private density estimation in the Wasserstein distance. We design and analyze instance-optimal algorithms for this problem that can adapt to easy instances. For distributions $P$ over $\mathbb{R}$, we consider a strong notion of instance-optimality: an algorithm that uniformly achieves the instance-optimal estimation rate is competitive with an algorithm that is told that the distribution is either $P$ or $Q_P$ for some distribution $Q_P$ whose probability density function (pdf) is within a factor of 2 of the pdf of $P$. For distributions over $\mathbb{R}^2$, we use a different notion of instance optimality. We say that an algorithm is instance-optimal if it is competitive with an algorithm that is given a constant-factor multiplicative approximation of the density of the distribution. We characterize the instance-optimal estimation rates in both these settings and show that they are uniformly achievable (up to polylogarithmic factors). Our approach for $\mathbb{R}^2$ extends to arbitrary metric spaces as it goes via hierarchically separated trees. As a special case our results lead to instance-optimal private learning in TV distance for discrete distributions.
Authors: Kurt Butler, Marija Iloska, Petar M. Djuric
Abstract: Counterfactual reasoning allows us to explore hypothetical scenarios in order to explain the impacts of our decisions. However, addressing such inquires is impossible without establishing the appropriate mathematical framework. In this work, we introduce the problem of counterfactual reasoning in the context of vector autoregressive (VAR) processes. We also formulate the inference of a causal model as a joint regression task where for inference we use both data with and without interventions. After learning the model, we exploit linearity of the VAR model to make exact predictions about the effects of counterfactual interventions. Furthermore, we quantify the total causal effects of past counterfactual interventions. The source code for this project is freely available at https://github.com/KurtButler/counterfactual_interventions.
URLs: https://github.com/KurtButler/counterfactual_interventions.
Authors: Yuhan Zhou, Fengjiao Tu, Kewei Sha, Junhua Ding, Haihua Chen
Abstract: Machine learning (ML) technologies have become substantial in practically all aspects of our society, and data quality (DQ) is critical for the performance, fairness, robustness, safety, and scalability of ML models. With the large and complex data in data-centric AI, traditional methods like exploratory data analysis (EDA) and cross-validation (CV) face challenges, highlighting the importance of mastering DQ tools. In this survey, we review 17 DQ evaluation and improvement tools in the last 5 years. By introducing the DQ dimensions, metrics, and main functions embedded in these tools, we compare their strengths and limitations and propose a roadmap for developing open-source DQ tools for ML. Based on the discussions on the challenges and emerging trends, we further highlight the potential applications of large language models (LLMs) and generative AI in DQ evaluation and improvement for ML. We believe this comprehensive survey can enhance understanding of DQ in ML and could drive progress in data-centric AI. A complete list of the literature investigated in this survey is available on GitHub at: https://github.com/haihua0913/awesome-dq4ml.
Authors: Ayumu Ueyama, Kazuhiko Kawamoto, Hiroshi Kera
Abstract: Weather forecasting is essential for various human activities. Recent data-driven models have outperformed numerical weather prediction by utilizing deep learning in forecasting performance. However, challenges remain in efficiently handling multiple meteorological variables. This study proposes a new variable aggregation scheme and an efficient learning framework for that challenge. Experiments show that VarteX outperforms the conventional model in forecast performance, requiring significantly fewer parameters and resources. The effectiveness of learning through multiple aggregations and regional split training is demonstrated, enabling more efficient and accurate deep learning-based weather forecasting.
Authors: Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee
Abstract: Optimization of convex functions under stochastic zeroth-order feedback has been a major and challenging question in online learning. In this work, we consider the problem of optimizing second-order smooth and strongly convex functions where the algorithm is only accessible to noisy evaluations of the objective function it queries. We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds. We propose an algorithm that features a combination of a bootstrapping stage and a mirror-descent stage. Our main technical innovation consists of a sharp characterization for the spherical-sampling gradient estimator under higher-order smoothness conditions, which allows the algorithm to optimally balance the bias-variance tradeoff, and a new iterative method for the bootstrapping stage, which maintains the performance for unbounded Hessian.
Authors: Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-Rung Lee
Abstract: The security and robustness of deep neural networks (DNNs) have become increasingly concerning. This paper aims to provide both a theoretical foundation and a practical solution to ensure the reliability of DNNs. We explore the concept of Lipschitz continuity to certify the robustness of DNNs against adversarial attacks, which aim to mislead the network with adding imperceptible perturbations into inputs. We propose a novel algorithm that remaps the input domain into a constrained range, reducing the Lipschitz constant and potentially enhancing robustness. Unlike existing adversarially trained models, where robustness is enhanced by introducing additional examples from other datasets or generative models, our method is almost cost-free as it can be integrated with existing models without requiring re-training. Experimental results demonstrate the generalizability of our method, as it can be combined with various models and achieve enhancements in robustness. Furthermore, our method achieves the best robust accuracy for CIFAR10, CIFAR100, and ImageNet datasets on the RobustBench leaderboard.
Authors: Peng Yan, Guodong Long, Jing Jiang, Michael Blumenstein
Abstract: Tackling non-IID data is an open challenge in federated learning research. Existing FL methods, including robust FL and personalized FL, are designed to improve model performance without consideration of interpreting non-IID across clients. This paper aims to design a novel FL method to robust and interpret the non-IID data across clients. Specifically, we interpret each client's dataset as a mixture of conceptual vectors that each one represents an interpretable concept to end-users. These conceptual vectors could be pre-defined or refined in a human-in-the-loop process or be learnt via the optimization procedure of the federated learning system. In addition to the interpretability, the clarity of client-specific personalization could also be applied to enhance the robustness of the training process on FL system. The effectiveness of the proposed method have been validated on benchmark datasets.
Authors: Xinghua Lou, Meet Dave, Shrinu Kushagra, Miguel Lazaro-Gredilla, Kevin Murphy
Abstract: We propose an approach to simulating trajectories of multiple interacting agents (road users) based on transformers and probabilistic graphical models (PGMs), and apply it to the Waymo SimAgents challenge. The transformer baseline is based on the MTR model, which predicts multiple future trajectories conditioned on the past trajectories and static road layout features. We then improve upon these generated trajectories using a PGM, which contains factors which encode prior knowledge, such as a preference for smooth trajectories, and avoidance of collisions with static obstacles and other moving agents. We perform (approximate) MAP inference in this PGM using the Gauss-Newton method. Finally we sample $K=32$ trajectories for each of the $N \sim 100$ agents for the next $T=8 \Delta$ time steps, where $\Delta=10$ is the sampling rate per second. Following the Model Predictive Control (MPC) paradigm, we only return the first element of our forecasted trajectories at each step, and then we replan, so that the simulation can constantly adapt to its changing environment. We therefore call our approach "Model Predictive Simulation" or MPS. We show that MPS improves upon the MTR baseline, especially in safety critical metrics such as collision rate. Furthermore, our approach is compatible with any underlying forecasting model, and does not require extra training, so we believe it is a valuable contribution to the community.
Authors: Justin Xu, Jack Gallifant, Alistair E. W. Johnson, Matthew B. A. McDermott
Abstract: Reproducibility remains a significant challenge in machine learning (ML) for healthcare. In this field, datasets, model pipelines, and even task/cohort definitions are often private, leading to a significant barrier in sharing, iterating, and understanding ML results on electronic health record (EHR) datasets. In this paper, we address a significant part of this problem by introducing the Automatic Cohort Extraction System for Event-Stream Datasets (ACES). This tool is designed to simultaneously simplify the development of task/cohorts for ML in healthcare and enable the reproduction of these cohorts, both at an exact level for single datasets and at a conceptual level across datasets. To accomplish this, ACES provides (1) a highly intuitive and expressive configuration language for defining both dataset-specific concepts and dataset-agnostic inclusion/exclusion criteria, and (2) a pipeline to automatically extract patient records that meet these defined criteria from real-world data. ACES can be automatically applied to any dataset in either the Medical Event Data Standard (MEDS) or EventStreamGPT (ESGPT) formats, or to *any* dataset for which the necessary task-specific predicates can be extracted in an event-stream form. ACES has the potential to significantly lower the barrier to entry for defining ML tasks, redefine the way researchers interact with EHR datasets, and significantly improve the state of reproducibility for ML studies in this modality. ACES is available at https://github.com/justin13601/aces.
Authors: Dong Liu, Meng Jiang, Kaiser Pister
Abstract: Currently, there are many quantization methods appeared for LLM quantization, yet few are user-friendly and easy to be deployed locally. Packages like TensorRT and Quantohave many underlying structures and self-invoking internal functions, which are not conducive to developers' personalized development and learning for deployment. Therefore, we develop LLMEasyQuant, it is a package aiming to for easy quantization deployment which is user-friendly and suitable for beginners' learning.
Authors: Amanda A. Howard, Bruno Jacob, Sarah H. Murphy, Alexander Heinlein, Panos Stinis
Abstract: Kolmogorov-Arnold networks (KANs) have attracted attention recently as an alternative to multilayer perceptrons (MLPs) for scientific machine learning. However, KANs can be expensive to train, even for relatively small networks. Inspired by finite basis physics-informed neural networks (FBPINNs), in this work, we develop a domain decomposition method for KANs that allows for several small KANs to be trained in parallel to give accurate solutions for multiscale problems. We show that finite basis KANs (FBKANs) can provide accurate results with noisy data and for physics-informed training.
Authors: Wonbeom Lee, Jungi Lee, Junghwan Seo, Jaewoong Sim
Abstract: Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory footprint of the transient state, known as the key-value (KV) cache, which scales with the sequence length and batch size. In this paper, we present InfiniGen, a novel KV cache management framework tailored for long-text generation, which synergistically works with modern offloading-based inference systems. InfiniGen leverages the key insight that a few important tokens that are essential for computing the subsequent attention layer in the Transformer can be speculated by performing a minimal rehearsal with the inputs of the current layer and part of the query weight and key cache of the subsequent layer. This allows us to prefetch only the essential KV cache entries (without fetching them all), thereby mitigating the fetch overhead from the host memory in offloading-based LLM serving systems. Our evaluation on several representative LLMs shows that InfiniGen improves the overall performance of a modern offloading-based system by up to 3.00x compared to prior KV cache management methods while offering substantially better model accuracy.
Authors: Ziming Zhao, Tiehua Zhang, Zhishu Shen, Hai Dong, Xingjun Ma, Xianhui Liu, Yun Yang
Abstract: In recent years, the widespread adoption of distributed microservice architectures within the industry has significantly increased the demand for enhanced system availability and robustness. Due to the complex service invocation paths and dependencies at enterprise-level microservice systems, it is challenging to locate the anomalies promptly during service invocations, thus causing intractable issues for normal system operations and maintenance. In this paper, we propose a Causal Heterogeneous grAph baSed framEwork for root cause analysis, namely CHASE, for microservice systems with multimodal data, including traces, logs, and system monitoring metrics. Specifically, related information is encoded into representative embeddings and further modeled by a multimodal invocation graph. Following that, anomaly detection is performed on each instance node with attentive heterogeneous message passing from its adjacent metric and log nodes. Finally, CHASE learns from the constructed hypergraph with hyperedges representing the flow of causality and performs root cause localization. We evaluate the proposed framework on two public microservice datasets with distinct attributes and compare with the state-of-the-art methods. The results show that CHASE achieves the average performance gain up to 36.2%(A@1) and 29.4%(Percentage@1), respectively to its best counterpart.
Authors: Trang Nguyen, Anh Tran, Nhat Ho
Abstract: Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering state-of-the-art performance, its impressive remembering capability can become a double-edged sword, raising security concerns as it might inadvertently retain poisoned knowledge injected during learning from private user data. Following this insight, in this paper, we expose continual learning to a potential threat: backdoor attack, which drives the model to follow a desired adversarial target whenever a specific trigger is present while still performing normally on clean samples. We highlight three critical challenges in executing backdoor attacks on incremental learners and propose corresponding solutions: (1) \emph{Transferability}: We employ a surrogate dataset and manipulate prompt selection to transfer backdoor knowledge to data from other suppliers; (2) \emph{Resiliency}: We simulate static and dynamic states of the victim to ensure the backdoor trigger remains robust during intense incremental learning processes; and (3) \emph{Authenticity}: We apply binary cross-entropy loss as an anti-cheating factor to prevent the backdoor trigger from devolving into adversarial noise. Extensive experiments across various benchmark datasets and continual learners validate our continual backdoor framework, achieving up to $100\%$ attack success rate, with further ablation studies confirming our contributions' effectiveness.
Authors: Emma Cramer, Bernd Frauenknecht, Ramil Sabirov, Sebastian Trimpe
Abstract: Combining Reinforcement Learning (RL) with a prior controller can yield the best out of two worlds: RL can solve complex nonlinear problems, while the control prior ensures safer exploration and speeds up training. Prior work largely blends both components with a fixed weight, neglecting that the RL agent's performance varies with the training progress and across regions in the state space. Therefore, we advocate for an adaptive strategy that dynamically adjusts the weighting based on the RL agent's current capabilities. We propose a new adaptive hybrid RL algorithm, Contextualized Hybrid Ensemble Q-learning (CHEQ). CHEQ combines three key ingredients: (i) a time-invariant formulation of the adaptive hybrid RL problem treating the adaptive weight as a context variable, (ii) a weight adaption mechanism based on the parametric uncertainty of a critic ensemble, and (iii) ensemble-based acceleration for data-efficient RL. Evaluating CHEQ on a car racing task reveals substantially stronger data efficiency, exploration safety, and transferability to unknown scenarios than state-of-the-art adaptive hybrid RL methods.
Authors: Yutong Chen, Hongzuo Xu, Guansong Pang, Hezhe Qiao, Yuan Zhou, Mingsheng Shang
Abstract: Time Series Anomaly Detection (TSAD) finds widespread applications across various domains such as financial markets, industrial production, and healthcare. Its primary objective is to learn the normal patterns of time series data, thereby identifying deviations in test samples. Most existing TSAD methods focus on modeling data from the temporal dimension, while ignoring the semantic information in the spatial dimension. To address this issue, we introduce a novel approach, called Spatial-Temporal Normality learning (STEN). STEN is composed of a sequence Order prediction-based Temporal Normality learning (OTN) module that captures the temporal correlations within sequences, and a Distance prediction-based Spatial Normality learning (DSN) module that learns the relative spatial relations between sequences in a feature space. By synthesizing these two modules, STEN learns expressive spatial-temporal representations for the normal patterns hidden in the time series data. Extensive experiments on five popular TSAD benchmarks show that STEN substantially outperforms state-of-the-art competing methods. Our code is available at https://github.com/mala-lab/STEN.
Authors: Indra Priyadarsini, Vidushi Sharma, Seiji Takeda, Akihiro Kishimoto, Lisa Hamada, Hajime Shinohara
Abstract: Development of efficient and high-performing electrolytes is crucial for advancing energy storage technologies, particularly in batteries. Predicting the performance of battery electrolytes rely on complex interactions between the individual constituents. Consequently, a strategy that adeptly captures these relationships and forms a robust representation of the formulation is essential for integrating with machine learning models to predict properties accurately. In this paper, we introduce a novel approach leveraging a transformer-based molecular representation model to effectively and efficiently capture the representation of electrolyte formulations. The performance of the proposed approach is evaluated on two battery property prediction tasks and the results show superior performance compared to the state-of-the-art methods.
Authors: William F. Whitney, Jacob Varley, Deepali Jain, Krzysztof Choromanski, Sumeet Singh, Vikas Sindhwani
Abstract: We present High-Density Visual Particle Dynamics (HD-VPD), a learned world model that can emulate the physical dynamics of real scenes by processing massive latent point clouds containing 100K+ particles. To enable efficiency at this scale, we introduce a novel family of Point Cloud Transformers (PCTs) called Interlacers leveraging intertwined linear-attention Performer layers and graph-based neighbour attention layers. We demonstrate the capabilities of HD-VPD by modeling the dynamics of high degree-of-freedom bi-manual robots with two RGB-D cameras. Compared to the previous graph neural network approach, our Interlacer dynamics is twice as fast with the same prediction quality, and can achieve higher quality using 4x as many particles. We illustrate how HD-VPD can evaluate motion plan quality with robotic box pushing and can grasping tasks. See videos and particle dynamics rendered by HD-VPD at https://sites.google.com/view/hd-vpd.
Authors: Lucas Beerens, Catherine F. Higham, Desmond J. Higham
Abstract: We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the deceptive diffusion model can create an arbitrary number of new, misclassified images that are not directly associated with training or test images. Deceptive diffusion offers the possibility of strengthening defence algorithms by providing adversarial training data at scale, including types of misclassification that are otherwise difficult to find. In our experiments, we also investigate the effect of training on a partially attacked data set. This highlights a new type of vulnerability for generative diffusion models: if an attacker is able to stealthily poison a portion of the training data, then the resulting diffusion model will generate a similar proportion of misleading outputs.
Authors: Marine Cauz, Adrien Bolland, Nicolas Wyrsch, Christophe Ballif
Abstract: The ongoing energy transition drives the development of decentralised renewable energy sources, which are heterogeneous and weather-dependent, complicating their integration into energy systems. This study tackles this issue by introducing a novel reinforcement learning (RL) framework tailored for the co-optimisation of design and control in energy systems. Traditionally, the integration of renewable sources in the energy sector has relied on complex mathematical modelling and sequential processes. By leveraging RL's model-free capabilities, the framework eliminates the need for explicit system modelling. By optimising both control and design policies jointly, the framework enhances the integration of renewable sources and improves system efficiency. This contribution paves the way for advanced RL applications in energy management, leading to more efficient and effective use of renewable energy sources.
Authors: Wenliang Zhong, Haoyu Tang, Qinghai Zheng, Mingzhu Xu, Yupeng Hu, Liqiang Nie
Abstract: The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data, prompting the development of Dataset Distillation methods to address the challenges of managing large datasets. Among these, Matching Training Trajectories (MTT) has been a prominent approach, which replicates the training trajectory of an expert network on real data with a synthetic dataset. However, our investigation found that this method suffers from three significant limitations: 1. Instability of expert trajectory generated by Stochastic Gradient Descent (SGD); 2. Low convergence speed of the distillation process; 3. High storage consumption of the expert trajectory. To address these issues, we offer a new perspective on understanding the essence of Dataset Distillation and MTT through a simple transformation of the objective function, and introduce a novel method called Matching Convexified Trajectory (MCT), which aims to provide better guidance for the student trajectory. MCT leverages insights from the linearized dynamics of Neural Tangent Kernel methods to create a convex combination of expert trajectories, guiding the student network to converge rapidly and stably. This trajectory is not only easier to store, but also enables a continuous sampling strategy during distillation, ensuring thorough learning and fitting of the entire expert trajectory. Comprehensive experiments across three public datasets validate the superiority of MCT over traditional MTT methods.
Authors: Tianjun Yao, Jiaqi Sun, Defu Cao, Kun Zhang, Guangyi Chen
Abstract: Recent works have introduced GNN-to-MLP knowledge distillation (KD) frameworks to combine both GNN's superior performance and MLP's fast inference speed. However, existing KD frameworks are primarily designed for node classification within single graphs, leaving their applicability to graph classification largely unexplored. Two main challenges arise when extending KD for node classification to graph classification: (1) The inherent sparsity of learning signals due to soft labels being generated at the graph level; (2) The limited expressiveness of student MLPs, especially in datasets with limited input feature spaces. To overcome these challenges, we introduce MuGSI, a novel KD framework that employs Multi-granularity Structural Information for graph classification. Specifically, we propose multi-granularity distillation loss in MuGSI to tackle the first challenge. This loss function is composed of three distinct components: graph-level distillation, subgraph-level distillation, and node-level distillation. Each component targets a specific granularity of the graph structure, ensuring a comprehensive transfer of structural knowledge from the teacher model to the student model. To tackle the second challenge, MuGSI proposes to incorporate a node feature augmentation component, thereby enhancing the expressiveness of the student MLPs and making them more capable learners. We perform extensive experiments across a variety of datasets and different teacher/student model architectures. The experiment results demonstrate the effectiveness, efficiency, and robustness of MuGSI. Codes are publicly available at: \textbf{\url{https://github.com/tianyao-aka/MuGSI}.}
Authors: Pietro Novelli, Marco Prattic\`o, Massimiliano Pontil, Carlo Ciliberto
Abstract: Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value functions. We address this challenge by introducing a novel approach based on learning a world model of the environment using conditional mean embeddings. We then leverage the operatorial formulation of RL to express the action-value function in terms of this quantity in closed form via matrix operations. Combining these estimators with PMD leads to POWR, a new RL algorithm for which we prove convergence rates to the global optimum. Preliminary experiments in finite and infinite state settings support the effectiveness of our method.
Authors: Minh-Tuan Tran
Abstract: User experience on mobile devices is constrained by limited battery capacity and processing power, but 6G technology advancements are diving rapidly into mobile technical evolution. Mobile edge computing (MEC) offers a solution, offloading computationally intensive tasks to edge cloud servers, reducing battery drain compared to local processing. The upcoming integrated sensing and communication in mobile communication may improve the trajectory prediction and processing delays. This study proposes a greedy resource allocation optimization strategy for multi-user networks to minimize aggregate energy usage. Numerical results show potential improvement at 33\% for every 1000 iteration. Addressing prediction model division and velocity accuracy issues is crucial for better results. A plan for further improvement and achieving objectives is outlined for the upcoming work phase.
Authors: Lev V. Utkin, Andrei V. Konstantinov, Stanislav R. Kirpichenko
Abstract: A method for solving concept-based learning (CBL) problem is proposed. The main idea behind the method is to divide each concept-annotated image into patches, to transform the patches into embeddings by using an autoencoder, and to cluster the embeddings assuming that each cluster will mainly contain embeddings of patches with certain concepts. To find concepts of a new image, the method implements the frequentist inference by computing prior and posterior probabilities of concepts based on rates of patches from images with certain values of the concepts. Therefore, the proposed method is called the Frequentist Inference CBL (FI-CBL). FI-CBL allows us to incorporate the expert rules in the form of logic functions into the inference procedure. An idea behind the incorporation is to update prior and conditional probabilities of concepts to satisfy the rules. The method is transparent because it has an explicit sequence of probabilistic calculations and a clear frequency interpretation. Numerical experiments show that FI-CBL outperforms the concept bottleneck model in cases when the number of training data is small. The code of proposed algorithms is publicly available.
Authors: Xinghao Wu, Xuefeng Liu, Jianwei Niu, Haolin Wang, Shaojie Tang, Guogang Zhu, Hao Su
Abstract: To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9\%.
Authors: Rui Pan, Jipeng Zhang, Xingyuan Pan, Renjie Pi, Xiaoyu Wang, Tong Zhang
Abstract: Bilevel optimization has shown its utility across various machine learning settings, yet most algorithms in practice require second-order information, making it challenging to scale them up. Only recently, a paradigm of first-order algorithms emerged, capable of effectively addressing bilevel optimization problems. Nevertheless, the practical efficiency of this paradigm remains unverified, particularly in the context of large language models (LLMs). This paper introduces the first scalable instantiation of this paradigm called ScaleBiO, focusing on bilevel optimization for large-scale LLM data reweighting. By combining with a recently proposed memory-efficient training technique called LISA, our novel algorithm allows the paradigm to scale to 34-billion-parameter LLMs on eight A40 GPUs, marking the first successful application of bilevel optimization under practical scenarios for large-sized LLMs. Empirically, extensive experiments on data reweighting verify the effectiveness of ScaleBiO for different-scaled models, including GPT-2, LLaMA-3-8B, GPT-NeoX-20B, and Yi-34B, where bilevel optimization succeeds in filtering irrelevant data samples and selecting informative samples. Theoretically, ScaleBiO ensures the optimality of the learned data weights, along with a convergence guarantee matching the conventional first-order bilevel optimization paradigm on smooth and strongly convex objectives.
Authors: Abolfazl Zarghani
Abstract: Diabetes mellitus is a chronic metabolic disorder that has emerged as one of the major health problems worldwide due to its high prevalence and serious complications, which are pricey to manage. Effective management requires good glycemic control and regular follow-up in the clinic; however, non-adherence to scheduled follow-ups is very common. This study uses the Diabetes 130-US Hospitals dataset for analysis and prediction of readmission patients by various traditional machine learning models, such as XGBoost, LightGBM, CatBoost, Decision Tree, and Random Forest, and also uses an in-house LSTM neural network for comparison. The quality of the data was assured by preprocessing it, and the performance evaluation for all these models was based on accuracy, precision, recall, and F1-score. LightGBM turned out to be the best traditional model, while XGBoost was the runner-up. The LSTM model suffered from overfitting despite high training accuracy. A major strength of LSTM is capturing temporal dependencies among the patient data. Further, SHAP values were used, which improved model interpretability, whereby key factors among them number of lab procedures and discharge disposition were identified as critical in the prediction of readmissions. This study demonstrates that model selection, validation, and interpretability are key steps in predictive healthcare modeling. This will help health providers design interventions for improved follow-up adherence and better management of diabetes.
Authors: Javier Blanco-Romero, Vicente Lorenzo, Florina Almenares Mendoza, Daniel D\'iaz-S\'anchez
Abstract: This study investigates the application of machine learning predictors for min-entropy estimation in Random Number Generators (RNGs), a key component in cryptographic applications where accurate entropy assessment is essential for cybersecurity. Our research indicates that these predictors, and indeed any predictor that leverages sequence correlations, primarily estimate average min-entropy, a metric not extensively studied in this context. We explore the relationship between average min-entropy and the traditional min-entropy, focusing on their dependence on the number of target bits being predicted. Utilizing data from Generalized Binary Autoregressive Models, a subset of Markov processes, we demonstrate that machine learning models (including a hybrid of convolutional and recurrent Long Short-Term Memory layers and the transformer-based GPT-2 model) outperform traditional NIST SP 800-90B predictors in certain scenarios. Our findings underscore the importance of considering the number of target bits in min-entropy assessment for RNGs and highlight the potential of machine learning approaches in enhancing entropy estimation techniques for improved cryptographic security.
Authors: Wael Mattar, Idan Levy, Nir Sharon, Shai Dekel
Abstract: In this paper, we take a new approach to autoregressive image generation that is based on two main ingredients. The first is wavelet image coding, which allows to tokenize the visual details of an image from coarse to fine details by ordering the information starting with the most significant bits of the most significant wavelet coefficients. The second is a variant of a language transformer whose architecture is re-designed and optimized for token sequences in this 'wavelet language'. The transformer learns the significant statistical correlations within a token sequence, which are the manifestations of well-known correlations between the wavelet subbands at various resolutions. We show experimental results with conditioning on the generation process.
Authors: Ying Cao, Zhaoxian Wu, Kun Yuan, Ali H. Sayed
Abstract: This paper proposes a theoretical framework to evaluate and compare the performance of gradient-descent algorithms for distributed learning in relation to their behavior around local minima in nonconvex environments. Previous works have noticed that convergence toward flat local minima tend to enhance the generalization ability of learning algorithms. This work discovers two interesting results. First, it shows that decentralized learning strategies are able to escape faster away from local minimizers and favor convergence toward flatter minima relative to the centralized solution in the large-batch training regime. Second, and importantly, the ultimate classification accuracy is not solely dependent on the flatness of the local minimizer but also on how well a learning algorithm can approach that minimum. In other words, the classification accuracy is a function of both flatness and optimization performance. The paper examines the interplay between the two measures of flatness and optimization error closely. One important conclusion is that decentralized strategies of the diffusion type deliver enhanced classification accuracy because it strikes a more favorable balance between flatness and optimization performance.
Authors: Mohamed Karim Belaid, Maximilian Rabus, Eyke H\"ullermeier
Abstract: Pairwise difference learning (PDL) has recently been introduced as a new meta-learning technique for regression. Instead of learning a mapping from instances to outcomes in the standard way, the key idea is to learn a function that takes two instances as input and predicts the difference between the respective outcomes. Given a function of this kind, predictions for a query instance are derived from every training example and then averaged. This paper extends PDL toward the task of classification and proposes a meta-learning technique for inducing a PDL classifier by solving a suitably defined (binary) classification problem on a paired version of the original training data. We analyze the performance of the PDL classifier in a large-scale empirical study and find that it outperforms state-of-the-art methods in terms of prediction performance. Last but not least, we provide an easy-to-use and publicly available implementation of PDL in a Python package.
Authors: Michael Canesche, Gaurav Verma, Fernando Magno Quintao Pereira
Abstract: Machine-learning models consist of kernels, which are algorithms applying operations on tensors -- data indexed by a linear combination of natural numbers. Examples of kernels include convolutions, transpositions, and vectorial products. There are many ways to implement a kernel. These implementations form the kernel's optimization space. Kernel scheduling is the problem of finding the best implementation, given an objective function -- typically execution speed. Kernel optimizers such as Ansor, Halide, and AutoTVM solve this problem via search heuristics, which combine two phases: exploration and exploitation. The first step evaluates many different kernel optimization spaces. The latter tries to improve the best implementations by investigating a kernel within the same space. For example, Ansor combines kernel generation through sketches for exploration and leverages an evolutionary algorithm to exploit the best sketches. In this work, we demonstrate the potential to reduce Ansor's search time while enhancing kernel quality by incorporating Droplet Search, an AutoTVM algorithm, into Ansor's exploration phase. The approach involves limiting the number of samples explored by Ansor, selecting the best, and exploiting it with a coordinate descent algorithm. By applying this approach to the first 300 kernels that Ansor generates, we usually obtain better kernels in less time than if we let Ansor analyze 10,000 kernels. This result has been replicated in 20 well-known deep-learning models (AlexNet, ResNet, VGG, DenseNet, etc.) running on four architectures: an AMD Ryzen 7 (x86), an NVIDIA A100 tensor core, an NVIDIA RTX 3080 GPU, and an ARM A64FX. A patch with this combined approach was approved in Ansor in February 2024. As evidence of the generality of this search methodology, a similar patch, achieving equally good results, was submitted to TVM's MetaSchedule in June 2024.
Authors: Daniel Sikar, Artur Garcez
Abstract: We posit that data can only be safe to use up to a certain threshold of the data distribution shift, after which control must be relinquished by the autonomous system and operation halted or handed to a human operator. With the use of a computer vision toy example we demonstrate that network predictive accuracy is impacted by data distribution shifts and propose distance metrics between training and testing data to define safe operation limits within said shifts. We conclude that beyond an empirically obtained threshold of the data distribution shift, it is unreasonable to expect network predictive accuracy not to degrade
Authors: Qian Xie, Raul Astudillo, Peter Frazier, Ziv Scully, Alexander Terenin
Abstract: Bayesian optimization is a technique for efficiently optimizing unknown functions in a black-box manner. To handle practical settings where gathering data requires use of finite resources, it is desirable to explicitly incorporate function evaluation costs into Bayesian optimization policies. To understand how to do so, we develop a previously-unexplored connection between cost-aware Bayesian optimization and the Pandora's Box problem, a decision problem from economics. The Pandora's Box problem admits a Bayesian-optimal solution based on an expression called the Gittins index, which can be reinterpreted as an acquisition function. We study the use of this acquisition function for cost-aware Bayesian optimization, and demonstrate empirically that it performs well, particularly in medium-high dimensions. We further show that this performance carries over to classical Bayesian optimization without explicit evaluation costs. Our work constitutes a first step towards integrating techniques from Gittins index theory into Bayesian optimization.
Authors: Tianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, Yaodong Yang
Abstract: Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic moral practices on a broad scale. We introduce progress alignment as a technical solution to mitigate this imminent risk. Progress alignment algorithms learn to emulate the mechanics of human moral progress, thereby addressing the susceptibility of existing alignment methods to contemporary moral blindspots. To empower research in progress alignment, we introduce ProgressGym, an experimental framework allowing the learning of moral progress mechanics from history, in order to facilitate future progress in real-world moral decisions. Leveraging 9 centuries of historical text and 18 historical LLMs, ProgressGym enables codification of real-world progress alignment challenges into concrete benchmarks. Specifically, we introduce three core challenges: tracking evolving values (PG-Follow), preemptively anticipating moral progress (PG-Predict), and regulating the feedback loop between human and AI value shifts (PG-Coevolve). Alignment methods without a temporal dimension are inapplicable to these tasks. In response, we present lifelong and extrapolative algorithms as baseline methods of progress alignment, and build an open leaderboard soliciting novel algorithms and challenges. The framework and the leaderboard are available at https://github.com/PKU-Alignment/ProgressGym and https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard respectively.
URLs: https://github.com/PKU-Alignment/ProgressGym, https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard
Authors: Dara Gold, Steven Rosenberg
Abstract: Gradient descent, or negative gradient flow, is a standard technique in optimization to find minima of functions. Many implementations of gradient descent rely on discretized versions, i.e., moving in the gradient direction for a set step size, recomputing the gradient, and continuing. In this paper, we present an approach to manifold learning where gradient descent takes place in the infinite dimensional space $\mathcal{E} = {\rm Emb}(M,\mathbb{R}^N)$ of smooth embeddings $\phi$ of a manifold $M$ into $\mathbb{R}^N$. Implementing a discretized version of gradient descent for $P:\mathcal{E}\to {\mathbb R}$, a penalty function that scores an embedding $\phi \in \mathcal{E}$, requires estimating how far we can move in a fixed direction -- the direction of one gradient step -- before leaving the space of smooth embeddings. Our main result is to give an explicit lower bound for this step length in terms of the Riemannian geometry of $\phi(M)$. In particular, we consider the case when the gradient of $P$ is pointwise normal to the embedded manifold $\phi(M)$. We prove this case arises when $P$ is invariant under diffeomorphisms of $M$, a natural condition in manifold learning.
Authors: Creighton Heaukulani, Abhinav Pandey, Lancelot F. James
Abstract: Modeling the trading volume curves of financial instruments throughout the day is of key interest in financial trading applications. Predictions of these so-called volume profiles guide trade execution strategies, for example, a common strategy is to trade a desired quantity across many orders in line with the expected volume curve throughout the day so as not to impact the price of the instrument. The volume curves (for each day) are naturally grouped by stock and can be further gathered into higher-level groupings, such as by industry. In order to model such admixtures of volume curves, we introduce a hierarchical Poisson process model for the intensity functions of admixtures of inhomogenous Poisson processes, which represent the trading times of the stock throughout the day. The model is based on the hierarchical Dirichlet process, and an efficient Markov Chain Monte Carlo (MCMC) algorithm is derived following the slice sampling framework for Bayesian nonparametric mixture models. We demonstrate the method on datasets of different stocks from the Trade and Quote repository maintained by Wharton Research Data Services, including the most liquid stock on the NASDAQ stock exchange, Apple, demonstrating the scalability of the approach.
Authors: Wojciech Wisniewski, Yuri Kalnishkan, David Lindsay, Si\^an Lindsay
Abstract: Financial organisations such as brokers face a significant challenge in servicing the investment needs of thousands of their traders worldwide. This task is further compounded since individual traders will have their own risk appetite and investment goals. Traders may look to capture short-term trends in the market which last only seconds to minutes, or they may have longer-term views which last several days to months. To reduce the complexity of this task, client trades can be clustered. By examining such clusters, we would likely observe many traders following common patterns of investment, but how do these patterns vary through time? Knowledge regarding the temporal distributions of such clusters may help financial institutions manage the overall portfolio of risk that accumulates from underlying trader positions. This study contributes to the field by demonstrating that the distribution of clusters derived from the real-world trades of 20k Foreign Exchange (FX) traders (from 2015 to 2017) is described in accordance with Ewens' Sampling Distribution. Further, we show that the Aggregating Algorithm (AA), an on-line prediction with expert advice algorithm, can be applied to the aforementioned real-world data in order to improve the returns of portfolios of trader risk. However we found that the AA 'struggles' when presented with too many trader ``experts'', especially when there are many trades with similar overall patterns. To help overcome this challenge, we have applied and compared the use of Statistically Validated Networks (SVN) with a hierarchical clustering approach on a subset of the data, demonstrating that both approaches can be used to significantly improve results of the AA in terms of profitability and smoothness of returns.
Authors: Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Abstract: In this paper, we introduce an enhanced textual adversarial attack method, known as Saliency Attention and Semantic Similarity driven adversarial Perturbation (SASSP). The proposed scheme is designed to improve the effectiveness of contextual perturbations by integrating saliency, attention, and semantic similarity. Traditional adversarial attack methods often struggle to maintain semantic consistency and coherence while effectively deceiving target models. Our proposed approach addresses these challenges by incorporating a three-pronged strategy for word selection and perturbation. First, we utilize a saliency-based word selection to prioritize words for modification based on their importance to the model's prediction. Second, attention mechanisms are employed to focus perturbations on contextually significant words, enhancing the attack's efficacy. Finally, an advanced semantic similarity-checking method is employed that includes embedding-based similarity and paraphrase detection. By leveraging models like Sentence-BERT for embedding similarity and fine-tuned paraphrase detection models from the Sentence Transformers library, the scheme ensures that the perturbed text remains contextually appropriate and semantically consistent with the original. Empirical evaluations demonstrate that SASSP generates adversarial examples that not only maintain high semantic fidelity but also effectively deceive state-of-the-art natural language processing models. Moreover, in comparison to the original scheme of contextual perturbation CLARE, SASSP has yielded a higher attack success rate and lower word perturbation rate.
Authors: Parley R Yang, Alexander Y Shestopaloff
Abstract: We demonstrate the use of Conditional Variational Encoder (CVAE) to improve the forecasts of daily stock volume time series in both short and long term forecasting tasks, with the use of advanced information of input variables such as rebalancing dates. CVAE generates non-linear time series as out-of-sample forecasts, which have better accuracy and closer fit of correlation to the actual data, compared to traditional linear models. These generative forecasts can also be used for scenario generation, which aids interpretation. We further discuss correlations in non-stationary time series and other potential extensions from the CVAE forecasts.
Authors: Yue Xie, Jiawen Bi, Hongcheng Liu
Abstract: When the nonconvex problem is complicated by stochasticity, the sample complexity of stochastic first-order methods may depend linearly on the problem dimension, which is undesirable for large-scale problems. In this work, we propose dimension-insensitive stochastic first-order methods (DISFOMs) to address nonconvex optimization with expected-valued objective function. Our algorithms allow for non-Euclidean and non-smooth distance functions as the proximal terms. Under mild assumptions, we show that DISFOM using minibatches to estimate the gradient enjoys sample complexity of $ \mathcal{O} ( (\log d) / \epsilon^4 ) $ to obtain an $\epsilon$-stationary point. Furthermore, we prove that DISFOM employing variance reduction can sharpen this bound to $\mathcal{O} ( (\log d)^{2/3}/\epsilon^{10/3} )$, which perhaps leads to the best-known sample complexity result in terms of $d$. We provide two choices of the non-smooth distance functions, both of which allow for closed-form solutions to the proximal step. Numerical experiments are conducted to illustrate the dimension insensitive property of the proposed frameworks.
Authors: Qinwei Huang, Chen Luo, Alex B. Wu, Simon Khan, Hai Li, Qinru Qiu
Abstract: In a multi-agent system, agents share their local observations to gain global situational awareness for decision making and collaboration using a message passing system. When to send a message, how to encode a message, and how to leverage the received messages directly affect the effectiveness of the collaboration among agents. When training a multi-agent cooperative game using reinforcement learning (RL), the message passing system needs to be optimized together with the agent policies. This consequently increases the model's complexity and poses significant challenges to the convergence and performance of learning. To address this issue, we propose the Belief-map Assisted Multi-agent System (BAMS), which leverages a neuro-symbolic belief map to enhance training. The belief map decodes the agent's hidden state to provide a symbolic representation of the agent's understanding of the environment and other agent's status. The simplicity of symbolic representation allows the gathering and comparison of the ground truth information with the belief, which provides an additional channel of feedback for the learning. Compared to the sporadic and delayed feedback coming from the reward in RL, the feedback from the belief map is more consistent and reliable. Agents using BAMS can learn a more effective message passing network to better understand each other, resulting in better performance in a cooperative predator and prey game with varying levels of map complexity and compare it to previous multi-agent message passing models. The simulation results showed that BAMS reduced training epochs by 66\%, and agents who apply the BAMS model completed the game with 34.62\% fewer steps on average.
Authors: Shouchang Guo, Sonam Damani, Keng-hao Chang
Abstract: In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This approach eliminates the need for hand-crafted prompt engineering or explicit model fine-tuning. Prompt tuning is significantly more parameter-efficient than model fine-tuning, as it involves optimizing partial inputs of language models to produce desired outputs. In this work, we aim to further reduce the amount of trainable parameters required for a language model to perform well on specific tasks. We propose Low-rank Prompt Tuning (LoPT), a low-rank model for prompts that achieves efficient prompt optimization. The proposed method demonstrates similar outcomes to full parameter prompt tuning while reducing the number of trainable parameters by a factor of 5. It also provides promising results compared to the state-of-the-art methods that would require 10 to 20 times more parameters.
Authors: Jiahai Feng, Stuart Russell, Jacob Steinhardt
Abstract: Language models are susceptible to bias, sycophancy, backdoors, and other tendencies that lead to unfaithful responses to the input context. Interpreting internal states of language models could help monitor and correct unfaithful behavior. We hypothesize that language models represent their input contexts in a latent world model, and seek to extract this latent world state from the activations. We do so with 'propositional probes', which compositionally probe tokens for lexical information and bind them into logical propositions representing the world state. For example, given the input context ''Greg is a nurse. Laura is a physicist.'', we decode the propositions ''WorksAs(Greg, nurse)'' and ''WorksAs(Laura, physicist)'' from the model's activations. Key to this is identifying a 'binding subspace' in which bound tokens have high similarity (''Greg'' and ''nurse'') but unbound ones do not (''Greg'' and ''physicist''). We validate propositional probes in a closed-world setting with finitely many predicates and properties. Despite being trained on simple templated contexts, propositional probes generalize to contexts rewritten as short stories and translated to Spanish. Moreover, we find that in three settings where language models respond unfaithfully to the input context -- prompt injections, backdoor attacks, and gender bias -- the decoded propositions remain faithful. This suggests that language models often encode a faithful world model but decode it unfaithfully, which motivates the search for better interpretability tools for monitoring LMs.
Authors: Connor Robertson, Cosmin Safta, Nicholson Collier, Jonathan Ozik, Jaideep Ray
Abstract: Agent-based models (ABM) provide an excellent framework for modeling outbreaks and interventions in epidemiology by explicitly accounting for diverse individual interactions and environments. However, these models are usually stochastic and highly parametrized, requiring precise calibration for predictive performance. When considering realistic numbers of agents and properly accounting for stochasticity, this high dimensional calibration can be computationally prohibitive. This paper presents a random forest based surrogate modeling technique to accelerate the evaluation of ABMs and demonstrates its use to calibrate an epidemiological ABM named CityCOVID via Markov chain Monte Carlo (MCMC). The technique is first outlined in the context of CityCOVID's quantities of interest, namely hospitalizations and deaths, by exploring dimensionality reduction via temporal decomposition with principal component analysis (PCA) and via sensitivity analysis. The calibration problem is then presented and samples are generated to best match COVID-19 hospitalization and death numbers in Chicago from March to June in 2020. These results are compared with previous approximate Bayesian calibration (IMABC) results and their predictive performance is analyzed showing improved performance with a reduction in computation.
Authors: Majd Saleh, Sarra Baghdadi, St\'ephane Paquelet
Abstract: Text segmentation holds paramount importance in the field of Natural Language Processing (NLP). It plays an important role in several NLP downstream tasks like information retrieval and document summarization. In this work, we propose a new solution, namely TocBERT, for segmenting texts using bidirectional transformers. TocBERT represents a supervised solution trained on the detection of titles and sub-titles from their semantic representations. This task was formulated as a named entity recognition (NER) problem. The solution has been applied on a medical text segmentation use-case where the Bio-ClinicalBERT model is fine-tuned to segment discharge summaries of the MIMIC-III dataset. The performance of TocBERT has been evaluated on a human-labeled ground truth corpus of 250 notes. It achieved an F1-score of 84.6% when evaluated on a linear text segmentation problem and 72.8% on a hierarchical text segmentation problem. It outperformed a carefully designed rule-based solution, particularly in distinguishing titles from subtitles.
Authors: Meiling Hao, Pingfan Su, Liyuan Hu, Zoltan Szabo, Qingyuan Zhao, Chengchun Shi
Abstract: Off-policy evaluation (OPE) is crucial for evaluating a target policy's impact offline before its deployment. However, achieving accurate OPE in large state spaces remains challenging.This paper studies state abstractions-originally designed for policy learning-in the context of OPE. Our contributions are three-fold: (i) We define a set of irrelevance conditions central to learning state abstractions for OPE. (ii) We derive sufficient conditions for achieving irrelevance in Q-functions and marginalized importance sampling ratios, the latter obtained by constructing a time-reversed Markov decision process (MDP) based on the observed MDP. (iii) We propose a novel two-step procedure that sequentially projects the original state space into a smaller space, which substantially simplify the sample complexity of OPE arising from high cardinality.
Authors: Ismail Alkhouri, Cedric Le Denmat, Yingjie Li, Cunxi Yu, Jia Liu, Rongrong Wang, Alvaro Velasquez
Abstract: Combinatorial Optimization (CO) plays a crucial role in addressing various significant problems, among them the challenging Maximum Independent Set (MIS) problem. In light of recent advancements in deep learning methods, efforts have been directed towards leveraging data-driven learning approaches, typically rooted in supervised learning and reinforcement learning, to tackle the NP-hard MIS problem. However, these approaches rely on labeled datasets, exhibit weak generalization, and often depend on problem-specific heuristics. Recently, ReLU-based dataless neural networks were introduced to address combinatorial optimization problems. This paper introduces a novel dataless quadratic neural network formulation, featuring a continuous quadratic relaxation for the MIS problem. Notably, our method eliminates the need for training data by treating the given MIS instance as a trainable entity. More specifically, the graph structure and constraints of the MIS instance are used to define the structure and parameters of the neural network such that training it on a fixed input provides a solution to the problem, thereby setting it apart from traditional supervised or reinforcement learning approaches. By employing a gradient-based optimization algorithm like ADAM and leveraging an efficient off-the-shelf GPU parallel implementation, our straightforward yet effective approach demonstrates competitive or superior performance compared to state-of-the-art learning-based methods. Another significant advantage of our approach is that, unlike exact and heuristic solvers, the running time of our method scales only with the number of nodes in the graph, not the number of edges.
Authors: Jitendra Bhandari, Animesh Basak Chowdhury, Ozgur Sinanoglu, Siddharth Garg, Ramesh Karri, Johann Knechtel
Abstract: Power side-channel (PSC) analysis is pivotal for securing cryptographic hardware. Prior art focused on securing gate-level netlists obtained as-is from chip design automation, neglecting all the complexities and potential side-effects for security arising from the design automation process. That is, automation traditionally prioritizes power, performance, and area (PPA), sidelining security. We propose a "security-first" approach, refining the logic synthesis stage to enhance the overall resilience of PSC countermeasures. We introduce ASCENT, a learning-and-search-based framework that (i) drastically reduces the time for post-design PSC evaluation and (ii) explores the security-vs-PPA design space. Thus, ASCENT enables an efficient exploration of a large number of candidate netlists, leading to an improvement in PSC resilience compared to regular PPA-optimized netlists. ASCENT is up to 120x faster than traditional PSC analysis and yields a 3.11x improvement for PSC resilience of state-of-the-art PSC countermeasures
Authors: Florin Pop, Judd Rosenblatt, Diogo Schwerz de Lucena, Michael Vaiana
Abstract: In this paper, we investigate the degree to which fine-tuning in Large Language Models (LLMs) effectively mitigates versus merely conceals undesirable behavior. Through the lens of semi-realistic role-playing exercises designed to elicit such behaviors, we explore the response dynamics of LLMs post fine-tuning interventions. Our methodology involves prompting models for Chain-of-Thought (CoT) reasoning and analyzing the coherence between the reasoning traces and the resultant outputs. Notably, we identify a pervasive phenomenon we term \emph{reason-based deception}, where models either stop producing reasoning traces or produce seemingly ethical reasoning traces that belie the unethical nature of their final outputs. We further examine the efficacy of response strategies (polite refusal versus explicit rebuttal) in curbing the occurrence of undesired behavior in subsequent outputs of multi-turn interactions. Our findings reveal that explicit rebuttals significantly outperform polite refusals in preventing the continuation of undesired outputs and nearly eliminate reason-based deception, challenging current practices in model fine-tuning. Accordingly, the two key contributions of this paper are (1) defining and studying reason-based deception, a new type of hidden behavior, and (2) demonstrating that rebuttals provide a more robust response model to harmful requests than refusals, thereby highlighting the need to reconsider the response strategies in fine-tuning approaches.
Authors: Muhammad Awais, Mehaboobathunnisa Sahul Hameed, Bidisha Bhattacharya, Orly Reiner, Rao Muhammad Anwer
Abstract: Recent advances have enabled the study of human brain development using brain organoids derived from stem cells. Quantifying cellular processes like mitosis in these organoids offers insights into neurodevelopmental disorders, but the manual analysis is time-consuming, and existing datasets lack specific details for brain organoid studies. We introduce BOrg, a dataset designed to study mitotic events in the embryonic development of the brain using confocal microscopy images of brain organoids. BOrg utilizes an efficient annotation pipeline with sparse point annotations and techniques that minimize expert effort, overcoming limitations of standard deep learning approaches on sparse data. We adapt and benchmark state-of-the-art object detection and cell counting models on BOrg for detecting and analyzing mitotic cells across prophase, metaphase, anaphase, and telophase stages. Our results demonstrate these adapted models significantly improve mitosis analysis efficiency and accuracy for brain organoid research compared to existing methods. BOrg facilitates the development of automated tools to quantify statistics like mitosis rates, aiding mechanistic studies of neurodevelopmental processes and disorders. Data and code are available at https://github.com/awaisrauf/borg.
Authors: Yuxuan Zhang, T. M. Sazzad, Yangyang Song, Spencer J. Chang, Ritesh Chowdhry, Tomas Mejia, Anna Hampton, Shelby Kucharski, Stefan Gerber, Barry Tillman, Marcio F. R. Resende, William M. Hammond, Chris H. Wilson, Alina Zare, Sanjeev J. Koppal
Abstract: Hyper-spectral imaging has recently gained increasing attention for use in different applications, including agricultural investigation, ground tracking, remote sensing and many other. However, the high cost, large physical size and complicated operation process stop hyperspectral cameras from being employed for various applications and research fields. In this paper, we introduce a cost-efficient, compact and easy to use active illumination camera that may benefit many applications. We developed a fully functional prototype of such camera. With the hope of helping with agricultural research, we tested our camera for plant root imaging. In addition, a U-Net model for spectral reconstruction was trained by using a reference hyperspectral camera's data as ground truth and our camera's data as input. We demonstrated our camera's ability to obtain additional information over a typical RGB camera. In addition, the ability to reconstruct hyperspectral data from multi-spectral input makes our device compatible to models and algorithms developed for hyperspectral applications with no modifications required.
Authors: Tanjin Taher Toma, Yibo Wang, Andreas Gahlmann, Scott T. Acton
Abstract: Automatic cell tracking in dense environments is plagued by inaccurate correspondences and misidentification of parent-offspring relationships. In this paper, we introduce a novel cell tracking algorithm named DenseTrack, which integrates deep learning with mathematical model-based strategies to effectively establish correspondences between consecutive frames and detect cell division events in crowded scenarios. We formulate the cell tracking problem as a deep learning-based temporal sequence classification task followed by solving a constrained one-to-one matching optimization problem exploiting the classifier's confidence scores. Additionally, we present an eigendecomposition-based cell division detection strategy that leverages knowledge of cellular geometry. The performance of the proposed approach has been evaluated by tracking densely packed cells in 3D time-lapse image sequences of bacterial biofilm development. The experimental results on simulated as well as experimental fluorescence image sequences suggest that the proposed tracking method achieves superior performance in terms of both qualitative and quantitative evaluation measures compared to recent state-of-the-art cell tracking approaches.
Authors: Faruk Ahmed, Andrew Sellergren, Lin Yang, Shawn Xu, Boris Babenko, Abbi Ward, Niels Olson, Arash Mohtashamian, Yossi Matias, Greg S. Corrado, Quang Duong, Dale R. Webster, Shravya Shetty, Daniel Golden, Yun Liu, David F. Steiner, Ellery Wulczyn
Abstract: Microscopic interpretation of histopathology images underlies many important diagnostic and treatment decisions. While advances in vision-language modeling raise new opportunities for analysis of such images, the gigapixel-scale size of whole slide images (WSIs) introduces unique challenges. Additionally, pathology reports simultaneously highlight key findings from small regions while also aggregating interpretation across multiple slides, often making it difficult to create robust image-text pairs. As such, pathology reports remain a largely untapped source of supervision in computational pathology, with most efforts relying on region-of-interest annotations or self-supervision at the patch-level. In this work, we develop a vision-language model based on the BLIP-2 framework using WSIs paired with curated text from pathology reports. This enables applications utilizing a shared image-text embedding space, such as text or image retrieval for finding cases of interest, as well as integration of the WSI encoder with a frozen large language model (LLM) for WSI-based generative text capabilities such as report generation or AI-in-the-loop interactions. We utilize a de-identified dataset of over 350,000 WSIs and diagnostic text pairs, spanning a wide range of diagnoses, procedure types, and tissue types. We present pathologist evaluation of text generation and text retrieval using WSI embeddings, as well as results for WSI classification and workflow prioritization (slide-level triaging). Model-generated text for WSIs was rated by pathologists as accurate, without clinically significant error or omission, for 78% of WSIs on average. This work demonstrates exciting potential capabilities for language-aligned WSI embeddings.
Authors: Qinzi Zhang, Hoang Tran, Ashok Cutkosky
Abstract: We introduce a new zeroth-order algorithm for private stochastic optimization on nonconvex and nonsmooth objectives. Given a dataset of size $M$, our algorithm ensures $(\alpha,\alpha\rho^2/2)$-R\'enyi differential privacy and finds a $(\delta,\epsilon)$-stationary point so long as $M=\tilde\Omega\left(\frac{d}{\delta\epsilon^3} + \frac{d^{3/2}}{\rho\delta\epsilon^2}\right)$. This matches the optimal complexity of its non-private zeroth-order analog. Notably, although the objective is not smooth, we have privacy ``for free'' whenever $\rho \ge \sqrt{d}\epsilon$.
Authors: Saeed Rashidi, William Won, Sudarshan Srinivasan, Puneet Gupta, Tushar Krishna
Abstract: Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallelization strategy. However, high-performance compute and interconnects are needed for maximum speed-up and linear scaling of the system. Wafer-scale systems are a promising technology that allows for tightly integrating high-end accelerators with high-speed wafer-scale interconnects, making it an attractive platform for distributed training. However, the wafer-scale interconnect should offer high performance and flexibility for various parallelization strategies to enable maximum optimizations for compute and memory usage. In this paper, we propose FRED, a wafer-scale interconnect that is tailored for the high-BW requirements of wafer-scale networks and can efficiently execute communication patterns of different parallelization strategies. Furthermore, FRED supports in-switch collective communication execution that reduces the network traffic by approximately 2X. Our results show that FRED can improve the average end-to-end training time of ResNet-152, Transformer-17B, GPT-3, and Transformer-1T by 1.76X, 1.87X, 1.34X, and 1.4X, respectively when compared to a baseline waferscale 2D-Mesh fabric.
Authors: Alexander Kenneth Clarke, Agnese Grison, Irene Mendez Guerra, Pranav Mamidanna, Shihan Ma, Silvia Muceli, Dario Farina
Abstract: A major outstanding problem when interfacing with spinal motor neurons is how to accurately compensate for non-stationary effects in the signal during source separation routines, particularly when they cannot be estimated in advance. This forces current systems to instead use undifferentiated bulk signal, which limits the potential degrees of freedom for control. In this study we propose a potential solution, using an unsupervised learning algorithm to blindly correct for the effects of latent processes which drive the signal non-stationarities. We implement this methodology within the theoretical framework of a quasilinear version of independent component analysis (ICA). The proposed design, HarmonICA, sidesteps the identifiability problems of nonlinear ICA, allowing for equivalent predictability to linear ICA whilst retaining the ability to learn complex nonlinear relationships between non-stationary latents and their effects on the signal. We test HarmonICA on both invasive and non-invasive recordings both simulated and real, demonstrating an ability to blindly compensate for the non-stationary effects specific to each, and thus to significantly enhance the quality of a source separation routine.
Authors: Luke Dzwonczyk, Carmine Emanuele Cella, David Ban
Abstract: In this paper we present the first steps towards the creation of a tool which enables artists to create music visualizations using pre-trained, generative, machine learning models. First, we investigate the application of network bending, the process of applying transforms within the layers of a generative network, to image generation diffusion models by utilizing a range of point-wise, tensor-wise, and morphological operators. We identify a number of visual effects that result from various operators, including some that are not easily recreated with standard image editing tools. We find that this process allows for continuous, fine-grain control of image generation which can be helpful for creative applications. Next, we generate music-reactive videos using Stable Diffusion by passing audio features as parameters to network bending operators. Finally, we comment on certain transforms which radically shift the image and the possibilities of learning more about the latent space of Stable Diffusion based on these transforms.
Authors: Diksha Goel, Kristen Moore, Mingyu Guo, Derui Wang, Minjune Kim, Seyit Camtepe
Abstract: This paper addresses a significant gap in Autonomous Cyber Operations (ACO) literature: the absence of effective edge-blocking ACO strategies in dynamic, real-world networks. It specifically targets the cybersecurity vulnerabilities of organizational Active Directory (AD) systems. Unlike the existing literature on edge-blocking defenses which considers AD systems as static entities, our study counters this by recognizing their dynamic nature and developing advanced edge-blocking defenses through a Stackelberg game model between attacker and defender. We devise a Reinforcement Learning (RL)-based attack strategy and an RL-assisted Evolutionary Diversity Optimization-based defense strategy, where the attacker and defender improve each other strategy via parallel gameplay. To address the computational challenges of training attacker-defender strategies on numerous dynamic AD graphs, we propose an RL Training Facilitator that prunes environments and neural networks to eliminate irrelevant elements, enabling efficient and scalable training for large graphs. We extensively train the attacker strategy, as a sophisticated attacker model is essential for a robust defense. Our empirical results successfully demonstrate that our proposed approach enhances defender's proficiency in hardening dynamic AD graphs while ensuring scalability for large-scale AD.
Authors: Yiding Lu, Haobin Li, Yunfan Li, Yijie Lin, Xi Peng
Abstract: Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by various factors such as network structures and learning objectives. However, as pointed out in this survey, the essence of deep clustering lies in the incorporation and utilization of prior knowledge, which is largely ignored by existing works. From pioneering deep clustering methods based on data structure assumptions to recent contrastive clustering methods based on data augmentation invariances, the development of deep clustering intrinsically corresponds to the evolution of prior knowledge. In this survey, we provide a comprehensive review of deep clustering methods by categorizing them into six types of prior knowledge. We find that in general the prior innovation follows two trends, namely, i) from mining to constructing, and ii) from internal to external. Besides, we provide a benchmark on five widely-used datasets and analyze the performance of methods with diverse priors. By providing a novel prior knowledge perspective, we hope this survey could provide some novel insights and inspire future research in the deep clustering community.
Authors: Hao Liu (Tony), Junze (Tony), Ye, Jose Blanchet, Nian Si
Abstract: We study the problem of fusing pre-trained (auxiliary) generative models to enhance the training of a target generative model. We propose using KL-divergence weighted barycenters as an optimal fusion mechanism, in which the barycenter weights are optimally trained to minimize a suitable loss for the target population. While computing the optimal KL-barycenter weights can be challenging, we demonstrate that this process can be efficiently executed using diffusion score training when the auxiliary generative models are also trained based on diffusion score methods. Moreover, we show that our fusion method has a dimension-free sample complexity in total variation distance provided that the auxiliary models are well fitted for their own task and the auxiliary tasks combined capture the target well. The main takeaway of our method is that if the auxiliary models are well-trained and can borrow features from each other that are present in the target, our fusion method significantly improves the training of generative models. We provide a concise computational implementation of the fusion algorithm, and validate its efficiency in the low-data regime with numerical experiments involving mixtures models and image datasets.
Authors: Yufan Xia, Giuseppe Maria Junior Barca
Abstract: BLAS Level 3 operations are essential for scientific computing, but finding the optimal number of threads for multi-threaded implementations on modern multi-core systems is challenging. We present an extension to the Architecture and Data-Structure Aware Linear Algebra (ADSALA) library that uses machine learning to optimize the runtime of all BLAS Level 3 operations. Our method predicts the best number of threads for each operation based on the matrix dimensions and the system architecture. We test our method on two HPC platforms with Intel and AMD processors, using MKL and BLIS as baseline BLAS implementations. We achieve speedups of 1.5 to 3.0 for all operations, compared to using the maximum number of threads. We also analyze the runtime patterns of different BLAS operations and explain the sources of speedup. Our work shows the effectiveness and generality of the ADSALA approach for optimizing BLAS routines on modern multi-core systems.
Authors: William Yik, Sam J. Silva
Abstract: Neural network emulators have become an invaluable tool for a wide variety of climate and weather prediction tasks. While showing incredibly promising results, these networks do not have an inherent ability to produce equitable predictions. That is, they are not guaranteed to provide a uniform quality of prediction along any particular class or group of people. This potential for inequitable predictions motivates the need for explicit representations of fairness in these neural networks. To that end, we draw on methods for enforcing analytical physical constraints in neural networks to bias networks towards more equitable predictions. We demonstrate the promise of this methodology using the task of climate model emulation. Specifically, we propose a custom loss function which punishes emulators with unequal quality of predictions across any prespecified regions or category, here defined using human development index (HDI). This loss function weighs a standard loss metric such as mean squared error against another metric which captures inequity along the equity category (HDI), allowing us to adjust the priority of each term before training. Importantly, the loss function does not specify a particular definition of equity to bias the neural network towards, opening the door for custom fairness metrics. Our results show that neural climate emulators trained with our loss function provide more equitable predictions and that the equity metric improves with greater weighting in the loss function. We empirically demonstrate that while there is a tradeoff between accuracy and equity when prioritizing the latter during training, an appropriate selection of the equity priority hyperparameter can minimize loss of performance.
Authors: Pedro Faustini, Shakila Mahjabin Tonni, Annabelle McIver, Qiongkai Xu, Mark Dras
Abstract: Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in underlying writing characteristics. Methods to protect privacy can involve using representations inside models that are demonstrated not to detect sensitive attributes or -- for instance, in cases where users might not trust a model, the sort of scenario of interest here -- changing the raw text before models can have access to it. The goal is to rewrite text to prevent someone from inferring a sensitive attribute (e.g. the gender of the author, or their location by the writing style) whilst keeping the text useful for its original intention (e.g. the sentiment of a product review). The few works tackling this have focused on generative techniques. However, these often create extensively different texts from the original ones or face problems such as mode collapse. This paper explores a novel adaptation of adversarial attack techniques to manipulate a text to deceive a classifier w.r.t one task (privacy) whilst keeping the predictions of another classifier trained for another task (utility) unchanged. We propose IDT, a method that analyses predictions made by auxiliary and interpretable models to identify which tokens are important to change for the privacy task, and which ones should be kept for the utility task. We evaluate different datasets for NLP suitable for different tasks. Automatic and human evaluations show that IDT retains the utility of text, while also outperforming existing methods when deceiving a classifier w.r.t privacy task.
Authors: Eduardo de Conto, Blaise Genest, Arvind Easwaran
Abstract: The development of digital twins (DTs) for physical systems increasingly leverages artificial intelligence (AI), particularly for combining data from different sources or for creating computationally efficient, reduced-dimension models. Indeed, even in very different application domains, twinning employs common techniques such as model order reduction and modelization with hybrid data (that is, data sourced from both physics-based models and sensors). Despite this apparent generality, current development practices are ad-hoc, making the design of AI pipelines for digital twinning complex and time-consuming. Here we propose Function+Data Flow (FDF), a domain-specific language (DSL) to describe AI pipelines within DTs. FDF aims to facilitate the design and validation of digital twins. Specifically, FDF treats functions as first-class citizens, enabling effective manipulation of models learned with AI. We illustrate the benefits of FDF on two concrete use cases from different domains: predicting the plastic strain of a structure and modeling the electromagnetic behavior of a bearing.
Authors: Krishna C. Puvvada, Piotr \.Zelasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Boris Ginsburg
Abstract: Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and speech translation model, outperforms current state-of-the-art models - Whisper, OWSM, and Seamless-M4T on English, French, Spanish, and German languages, while being trained on an order of magnitude less data than these models. Three key factors enables such data-efficient model: (1) a FastConformer-based attention encoder-decoder architecture (2) training on synthetic data generated with machine translation and (3) advanced training techniques: data-balancing, dynamic data blending, dynamic bucketing and noise-robust fine-tuning. The model, weights, and training code will be open-sourced.
Authors: Loes Kruger, Sebastian Junges, Jurriaan Rot
Abstract: Active automata learning (AAL) is a method to infer state machines by interacting with black-box systems. Adaptive AAL aims to reduce the sample complexity of AAL by incorporating domain specific knowledge in the form of (similar) reference models. Such reference models appear naturally when learning multiple versions or variants of a software system. In this paper, we present state matching, which allows flexible use of the structure of these reference models by the learner. State matching is the main ingredient of adaptive L#, a novel framework for adaptive learning, built on top of L#. Our empirical evaluation shows that adaptive L# improves the state of the art by up to two orders of magnitude.
Authors: Nicola Garau, Giulia Martinelli, Niccol\`o Bisagno, Denis Tom\`e, Carsten Stoll
Abstract: Monocular Human Pose Estimation (HPE) aims at determining the 3D positions of human joints from a single 2D image captured by a camera. However, a single 2D point in the image may correspond to multiple points in 3D space. Typically, the uniqueness of the 2D-3D relationship is approximated using an orthographic or weak-perspective camera model. In this study, instead of relying on approximations, we advocate for utilizing the full perspective camera model. This involves estimating camera parameters and establishing a precise, unambiguous 2D-3D relationship. To do so, we introduce the EPOCH framework, comprising two main components: the pose lifter network (LiftNet) and the pose regressor network (RegNet). LiftNet utilizes the full perspective camera model to precisely estimate the 3D pose in an unsupervised manner. It takes a 2D pose and camera parameters as inputs and produces the corresponding 3D pose estimation. These inputs are obtained from RegNet, which starts from a single image and provides estimates for the 2D pose and camera parameters. RegNet utilizes only 2D pose data as weak supervision. Internally, RegNet predicts a 3D pose, which is then projected to 2D using the estimated camera parameters. This process enables RegNet to establish the unambiguous 2D-3D relationship. Our experiments show that modeling the lifting as an unsupervised task with a camera in-the-loop results in better generalization to unseen data. We obtain state-of-the-art results for the 3D HPE on the Human3.6M and MPI-INF-3DHP datasets. Our code is available at: [Github link upon acceptance, see supplementary materials].
Authors: Jihao Liu, Xin Huang, Jinliang Zheng, Boxiao Liu, Jia Wang, Osamu Yoshie, Yu Liu, Hongsheng Li
Abstract: This paper introduces MM-Instruct, a large-scale dataset of diverse and high-quality visual instruction data designed to enhance the instruction-following capabilities of large multimodal models (LMMs). While existing visual instruction datasets often focus on question-answering, they struggle to generalize to broader application scenarios such as creative writing, summarization, or image analysis. To address these limitations, we propose a novel approach to constructing MM-Instruct that leverages the strong instruction-following capabilities of existing LLMs to generate novel visual instruction data from large-scale but conventional image captioning datasets. MM-Instruct first leverages ChatGPT to automatically generate diverse instructions from a small set of seed instructions through augmenting and summarization. It then matches these instructions with images and uses an open-sourced large language model (LLM) to generate coherent answers to the instruction-image pairs. The LLM is grounded by the detailed text descriptions of images in the whole answer generation process to guarantee the alignment of the instruction data. Moreover, we introduce a benchmark based on the generated instruction data to evaluate the instruction-following capabilities of existing LMMs. We demonstrate the effectiveness of MM-Instruct by training a LLaVA-1.5 model on the generated data, denoted as LLaVA-Instruct, which exhibits significant improvements in instruction-following capabilities compared to LLaVA-1.5 models. The MM-Instruct dataset, benchmark, and pre-trained models are available at https://github.com/jihaonew/MM-Instruct.
Authors: Bharati. K, Vikesh Siddhu, Krishna Jagannathan
Abstract: Entanglement is a key resource for a wide range of tasks in quantum information and computing. Thus, verifying availability of this quantum resource is essential. Extensive research on entanglement detection has led to no-go theorems (Lu et al. [Phys. Rev. Lett., 116, 230501 (2016)]) that highlight the need for full state tomography (FST) in the absence of adaptive or joint measurements. Recent advancements, as proposed by Zhu, Teo, and Englert [Phys. Rev. A, 81, 052339, 2010], introduce a single-parameter family of entanglement witness measurements which are capable of conclusively detecting certain entangled states and only resort to FST when all witness measurements are inconclusive. We find a variety of realistic noisy two-qubit quantum states $\mathcal{F}$ that yield conclusive results under this witness family. We solve the problem of detecting entanglement among $K$ quantum states in $\mathcal{F}$, of which $m$ states are entangled, with $m$ potentially unknown. We recognize a structural connection of this problem to the Bad Arm Identification problem in stochastic Multi-Armed Bandits (MAB). In contrast to existing quantum bandit frameworks, we establish a new correspondence tailored for entanglement detection and term it the $(m,K)$-quantum Multi-Armed Bandit. We implement two well-known MAB policies for arbitrary states derived from $\mathcal{F}$, present theoretical guarantees on the measurement/sample complexity and demonstrate the practicality of the policies through numerical simulations. More broadly, this paper highlights the potential for employing classical machine learning techniques for quantum entanglement detection.
Authors: Ali Kazemi Arani, Triet Huynh Minh Le, Mansooreh Zahedi, M. Ali Babar
Abstract: Context: Machine learning (ML) and deep learning (DL) analyze raw data to extract valuable insights in specific phases. The rise of continuous practices in software projects emphasizes automating Continuous Integration (CI) with these learning-based methods, while the growing adoption of such approaches underscores the need for systematizing knowledge. Objective: Our objective is to comprehensively review and analyze existing literature concerning learning-based methods within the CI domain. We endeavour to identify and analyse various techniques documented in the literature, emphasizing the fundamental attributes of training phases within learning-based solutions in the context of CI. Method: We conducted a Systematic Literature Review (SLR) involving 52 primary studies. Through statistical and thematic analyses, we explored the correlations between CI tasks and the training phases of learning-based methodologies across the selected studies, encompassing a spectrum from data engineering techniques to evaluation metrics. Results: This paper presents an analysis of the automation of CI tasks utilizing learning-based methods. We identify and analyze nine types of data sources, four steps in data preparation, four feature types, nine subsets of data features, five approaches for hyperparameter selection and tuning, and fifteen evaluation metrics. Furthermore, we discuss the latest techniques employed, existing gaps in CI task automation, and the characteristics of the utilized learning-based techniques. Conclusion: This study provides a comprehensive overview of learning-based methods in CI, offering valuable insights for researchers and practitioners developing CI task automation. It also highlights the need for further research to advance these methods in CI.
Authors: Tobias Pett, Sebastian Krieter, Thomas Th\"um, Ina Schaefer
Abstract: Ensuring the functional safety of highly configurable systems often requires testing representative subsets of all possible configurations to reduce testing effort and save resources. The ratio of covered t-wise feature interactions (i.e., T-Wise Feature Interaction Coverage) is a common criterion for determining whether a subset of configurations is representative and capable of finding faults. Existing t-wise sampling algorithms uniformly cover t-wise feature interactions for all features, resulting in lengthy execution times and large sample sizes, particularly when large t-wise feature interactions are considered (i.e., high values of t). In this paper, we introduce a novel approach to t-wise feature interaction sampling, questioning the necessity of uniform coverage across all t-wise feature interactions, called \emph{\mulTiWise{}}. Our approach prioritizes between subsets of critical and non-critical features, considering higher t-values for subsets of critical features when generating a t-wise feature interaction sample. We evaluate our approach using subject systems from real-world applications, including \busybox{}, \soletta{}, \fiasco{}, and \uclibc{}. Our results show that sacrificing uniform t-wise feature interaction coverage between all features reduces the time needed to generate a sample and the resulting sample size. Hence, \mulTiWise{} Sampling offers an alternative to existing approaches if knowledge about feature criticality is available.
Authors: Ashish Sharma, SVSLN Surya Suhas Vaddhiparthy, Sai Usha Goparaju, Deepak Gangadharan, Harikumar Kandath
Abstract: This paper explores the critical issue of enhancing cybersecurity measures for low-cost, Wi-Fi-based Unmanned Aerial Vehicles (UAVs) against Distributed Denial of Service (DDoS) attacks. In the current work, we have explored three variants of DDoS attacks, namely Transmission Control Protocol (TCP), Internet Control Message Protocol (ICMP), and TCP + ICMP flooding attacks, and developed a detection mechanism that runs on the companion computer of the UAV system. As a part of the detection mechanism, we have evaluated various machine learning, and deep learning algorithms, such as XGBoost, Isolation Forest, Long Short-Term Memory (LSTM), Bidirectional-LSTM (Bi-LSTM), LSTM with attention, Bi-LSTM with attention, and Time Series Transformer (TST) in terms of various classification metrics. Our evaluation reveals that algorithms with attention mechanisms outperform their counterparts in general, and TST stands out as the most efficient model with a run time of 0.1 seconds. TST has demonstrated an F1 score of 0.999, 0.997, and 0.943 for TCP, ICMP, and TCP + ICMP flooding attacks respectively. In this work, we present the necessary steps required to build an on-board DDoS detection mechanism. Further, we also present the ablation study to identify the best TST hyperparameters for DDoS detection, and we have also underscored the advantage of adapting learnable positional embeddings in TST for DDoS detection with an improvement in F1 score from 0.94 to 0.99.
Authors: Micha{\l} Cholewa, Micha{\l} Romaszewski, Przemys{\l}aw G{\l}omb, Katarzyna Ko{\l}odziej, Micha{\l} Gorawski, Jakub Koral, Wojciech Koral, Andrzej Madej, Kryspin Musio{\l}
Abstract: In this article, we propose an approach to leak localisation in a complex water delivery grid with the use of data from physical simulation (e.g. EPANET software). This task is usually achieved by a network of multiple water pressure sensors and analysis of the so-called sensitivity matrix of pressure differences between the network's simulated data and actual data of the network affected by the leak. However, most algorithms using this approach require a significant number of pressure sensors -- a condition that is not easy to fulfil in the case of many less equipped networks. Therefore, we answer the question of whether leak localisation is possible by utilising very few sensors but having the ability to relocate one of them. Our algorithm is based on physical simulations (EPANET software) and an iterative scheme for mobile sensor relocation. The experiments show that the proposed system can equalise the low number of sensors with adjustments made for their positioning, giving a very good approximation of leak's position both in simulated cases and real-life example taken from BattLeDIM competition L-Town data.
Authors: Maciej Falkiewicz, Naoya Takeishi, Alexandros Kalousis
Abstract: We propose a novel deep generative model, the Kolmogorov-Smirnov Generative Adversarial Network (KSGAN). Unlike existing approaches, KSGAN formulates the learning process as a minimization of the Kolmogorov-Smirnov (KS) distance, generalized to handle multivariate distributions. This distance is calculated using the quantile function, which acts as the critic in the adversarial training process. We formally demonstrate that minimizing the KS distance leads to the trained approximate distribution aligning with the target distribution. We propose an efficient implementation and evaluate its effectiveness through experiments. The results show that KSGAN performs on par with existing adversarial methods, exhibiting stability during training, resistance to mode dropping and collapse, and tolerance to variations in hyperparameter settings. Additionally, we review the literature on the Generalized KS test and discuss the connections between KSGAN and existing adversarial generative models.
Authors: Yan Shuo Tan, Omer Ronen, Theo Saarinen, Bin Yu
Abstract: Bayesian Additive Regression Trees (BART) is a popular Bayesian non-parametric regression model that is commonly used in causal inference and beyond. Its strong predictive performance is supported by theoretical guarantees that its posterior distribution concentrates around the true regression function at optimal rates under various data generative settings and for appropriate prior choices. In this paper, we show that the BART sampler often converges slowly, confirming empirical observations by other researchers. Assuming discrete covariates, we show that, while the BART posterior concentrates on a set comprising all optimal tree structures (smallest bias and complexity), the Markov chain's hitting time for this set increases with $n$ (training sample size), under several common data generative settings. As $n$ increases, the approximate BART posterior thus becomes increasingly different from the exact posterior (for the same number of MCMC samples), contrasting with earlier concentration results on the exact posterior. This contrast is highlighted by our simulations showing worsening frequentist undercoverage for approximate posterior intervals and a growing ratio between the MSE of the approximate posterior and that obtainable by artificially improving convergence via averaging multiple sampler chains. Finally, based on our theoretical insights, possibilities are discussed to improve the BART sampler convergence performance.
Authors: Ryan P. Ringel, Zachary S. Charlick, Jiaxun Liu, Boxi Xia, Boyuan Chen
Abstract: Robot design has traditionally been costly and labor-intensive. Despite advancements in automated processes, it remains challenging to navigate a vast design space while producing physically manufacturable robots. We introduce Text2Robot, a framework that converts user text specifications and performance preferences into physical quadrupedal robots. Within minutes, Text2Robot can use text-to-3D models to provide strong initializations of diverse morphologies. Within a day, our geometric processing algorithms and body-control co-optimization produce a walking robot by explicitly considering real-world electronics and manufacturability. Text2Robot enables rapid prototyping and opens new opportunities for robot design with generative models.
Authors: Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang, Zhiqiang Tao
Abstract: Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce Self-Training Large Language and Vision Assistant for Medical (STLLaVA-Med). The proposed method is designed to train a policy model (an LVLM) capable of auto-generating medical visual instruction data to improve data efficiency, guided through Direct Preference Optimization (DPO). Specifically, a more powerful and larger LVLM (e.g., GPT-4o) is involved as a biomedical expert to oversee the DPO fine-tuning process on the auto-generated data, encouraging the policy model to align efficiently with human preferences. We validate the efficacy and data efficiency of STLLaVA-Med across three major medical Visual Question Answering (VQA) benchmarks, demonstrating competitive zero-shot performance with the utilization of only 9% of the medical data.
Authors: Habib Hajimolahoseini, Mohammad Hassanpour, Foozhan Ataiefard, Boxing Chen, Yang Liu
Abstract: This paper introduces a novel method of Progressive Low Rank Decomposition (PLRD) tailored for the compression of large language models. Our approach leverages a pre-trained model, which is then incrementally decompressed to smaller sizes using progressively lower ranks. This method allows for significant reductions in computational overhead and energy consumption, as subsequent models are derived from the original without the need for retraining from scratch. We detail the implementation of PLRD, which strategically decreases the tensor ranks, thus optimizing the trade-off between model performance and resource usage. The efficacy of PLRD is demonstrated through extensive experiments showing that models trained with PLRD method on only 1B tokens maintain comparable performance with traditionally trained models while using 0.1% of the tokens. The versatility of PLRD is highlighted by its ability to generate multiple model sizes from a single foundational model, adapting fluidly to varying computational and memory budgets. Our findings suggest that PLRD could set a new standard for the efficient scaling of LLMs, making advanced AI more feasible on diverse platforms.
Authors: Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt
Abstract: Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning interfaces, we introduce covert malicious finetuning, a method to compromise model safety via finetuning while evading detection. Our method constructs a malicious dataset where every individual datapoint appears innocuous, but finetuning on the dataset teaches the model to respond to encoded harmful requests with encoded harmful responses. Applied to GPT-4, our method produces a finetuned model that acts on harmful instructions 99% of the time and avoids detection by defense mechanisms such as dataset inspection, safety evaluations, and input/output classifiers. Our findings question whether black-box finetuning access can be secured against sophisticated adversaries.
Authors: Sara Sabour, Lily Goli, George Kopanas, Mark Matthews, Dmitry Lagun, Leonidas Guibas, Alec Jacobson, David J. Fleet, Andrea Tagliasacchi
Abstract: 3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications.However, current methods require highly controlled environments (no moving people or wind-blown elements, and consistent lighting) to meet the inter-view consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotlessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures.
Authors: XuDong Wang, Jingfeng Yang, Trevor Darrell
Abstract: The Segmentation Anything Model (SAM) requires labor-intensive data labeling. We present Unsupervised SAM (UnSAM) for promptable and automatic whole-image segmentation that does not require human annotations. UnSAM utilizes a divide-and-conquer strategy to "discover" the hierarchical structure of visual scenes. We first leverage top-down clustering methods to partition an unlabeled image into instance/semantic level segments. For all pixels within a segment, a bottom-up clustering method is employed to iteratively merge them into larger groups, thereby forming a hierarchical structure. These unsupervised multi-granular masks are then utilized to supervise model training. Evaluated across seven popular datasets, UnSAM achieves competitive results with the supervised counterpart SAM, and surpasses the previous state-of-the-art in unsupervised segmentation by 11% in terms of AR. Moreover, we show that supervised SAM can also benefit from our self-supervised labels. By integrating our unsupervised pseudo masks into SA-1B's ground-truth masks and training UnSAM with only 1% of SA-1B, a lightly semi-supervised UnSAM can often segment entities overlooked by supervised SAM, exceeding SAM's AR by over 6.7% and AP by 3.9% on SA-1B.
Authors: Sheridan Feucht, David Atkinson, Byron Wallace, David Bau
Abstract: LLMs process text as sequences of tokens that roughly correspond to words, where less common words are represented by multiple tokens. However, individual tokens are often semantically unrelated to the meanings of the words/concepts they comprise. For example, Llama-2-7b's tokenizer splits the word "northeastern" into the tokens ['_n', 'ort', 'he', 'astern'], none of which correspond to semantically meaningful units like "north" or "east." Similarly, the overall meanings of named entities like "Neil Young" and multi-word expressions like "break a leg" cannot be directly inferred from their constituent tokens. Mechanistically, how do LLMs convert such arbitrary groups of tokens into useful higher-level representations? In this work, we find that last token representations of named entities and multi-token words exhibit a pronounced "erasure" effect, where information about previous and current tokens is rapidly forgotten in early layers. Using this observation, we propose a method to "read out" the implicit vocabulary of an autoregressive LLM by examining differences in token representations across layers, and present results of this method for Llama-2-7b and Llama-3-8B. To our knowledge, this is the first attempt to probe the implicit vocabulary of an LLM.
Authors: Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, Dong Yu
Abstract: We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data. To fully exploit this methodology at scale, we introduce Persona Hub -- a collection of 1 billion diverse personas automatically curated from web data. These 1 billion personas (~13% of the world's total population), acting as distributed carriers of world knowledge, can tap into almost every perspective encapsulated within the LLM, thereby facilitating the creation of diverse synthetic data at scale for various scenarios. By showcasing Persona Hub's use cases in synthesizing high-quality mathematical and logical reasoning problems, instructions (i.e., user prompts), knowledge-rich texts, game NPCs and tools (functions) at scale, we demonstrate persona-driven data synthesis is versatile, scalable, flexible, and easy to use, potentially driving a paradigm shift in synthetic data creation and applications in practice, which may have a profound impact on LLM research and development.
Authors: Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo
Abstract: Large Language Models (LLMs) equipped with extensive world knowledge and strong reasoning skills can tackle diverse tasks across domains, often by posing them as conversation-style instruction-response pairs. In this paper, we propose LLaRA: Large Language and Robotics Assistant, a framework which formulates robot action policy as conversations, and provides improved responses when trained with auxiliary data that complements policy learning. LLMs with visual inputs, i.e., Vision Language Models (VLMs), have the capacity to process state information as visual-textual prompts and generate optimal policy decisions in text. To train such action policy VLMs, we first introduce an automated pipeline to generate diverse high-quality robotics instruction data from existing behavior cloning data. A VLM finetuned with the resulting collection of datasets based on a conversation-style formulation tailored for robotics tasks, can generate meaningful robot action policy decisions. Our experiments across multiple simulated and real-world environments demonstrate the state-of-the-art performance of the proposed LLaRA framework. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.
Authors: Yauhen Yakimenka, Chung-Wei Weng, Hsuan-Yin Lin, Eirik Rosnes, J\"org Kliewer
Abstract: We consider the straggler problem in decentralized learning over a logical ring while preserving user data privacy. Especially, we extend the recently proposed framework of differential privacy (DP) amplification by decentralization by Cyffers and Bellet to include overall training latency--comprising both computation and communication latency. Analytical results on both the convergence speed and the DP level are derived for both a skipping scheme (which ignores the stragglers after a timeout) and a baseline scheme that waits for each node to finish before the training continues. A trade-off between overall training latency, accuracy, and privacy, parameterized by the timeout of the skipping scheme, is identified and empirically validated for logistic regression on a real-world dataset and for image classification using the MNIST and CIFAR-10 datasets.
Authors: Weizhi Li, Prad Kadambi, Pouria Saidi, Karthikeyan Natesan Ramamurthy, Gautam Dasarathy, Visar Berisha
Abstract: A two-sample hypothesis test is a statistical procedure used to determine whether the distributions generating two samples are identical. We consider the two-sample testing problem in a new scenario where the sample measurements (or sample features) are inexpensive to access, but their group memberships (or labels) are costly. To address the problem, we devise the first \emph{active sequential two-sample testing framework} that not only sequentially but also \emph{actively queries}. Our test statistic is a likelihood ratio where one likelihood is found by maximization over all class priors, and the other is provided by a probabilistic classification model. The classification model is adaptively updated and used to predict where the (unlabelled) features have a high dependency on labels; labeling the ``high-dependency'' features leads to the increased power of the proposed testing framework. In theory, we provide the proof that our framework produces an \emph{anytime-valid} $p$-value. In addition, we characterize the proposed framework's gain in testing power by analyzing the mutual information between the feature and label variables in asymptotic and finite-sample scenarios. In practice, we introduce an instantiation of our framework and evaluate it using several experiments; the experiments on the synthetic, MNIST, and application-specific datasets demonstrate that the testing power of the instantiated active sequential test significantly increases while the Type I error is under control.
Authors: Eitan Rosen, Paulina Hoyos, Xiuyuan Cheng, Joe Kileel, Yoel Shkolnisky
Abstract: Graph Laplacian based algorithms for data lying on a manifold have been proven effective for tasks such as dimensionality reduction, clustering, and denoising. In this work, we consider data sets whose data points lie on a manifold that is closed under the action of a known unitary matrix Lie group G. We propose to construct the graph Laplacian by incorporating the distances between all the pairs of points generated by the action of G on the data set. We deem the latter construction the ``G-invariant Graph Laplacian'' (G-GL). We show that the G-GL converges to the Laplace-Beltrami operator on the data manifold, while enjoying a significantly improved convergence rate compared to the standard graph Laplacian which only utilizes the distances between the points in the given data set. Furthermore, we show that the G-GL admits a set of eigenfunctions that have the form of certain products between the group elements and eigenvectors of certain matrices, which can be estimated from the data efficiently using FFT-type algorithms. We demonstrate our construction and its advantages on the problem of filtering data on a noisy manifold closed under the action of the special unitary group SU(2).
Authors: Saba Ghaffari, Ehsan Saleh, Alexander G. Schwing, Yu-Xiong Wang, Martin D. Burke, Saurabh Sinha
Abstract: Protein design, a grand challenge of the day, involves optimization on a fitness landscape, and leading methods adopt a model-based approach where a model is trained on a training set (protein sequences and fitness) and proposes candidates to explore next. These methods are challenged by sparsity of high-fitness samples in the training set, a problem that has been in the literature. A less recognized but equally important problem stems from the distribution of training samples in the design space: leading methods are not designed for scenarios where the desired optimum is in a region that is not only poorly represented in training data, but also relatively far from the highly represented low-fitness regions. We show that this problem of "separation" in the design space is a significant bottleneck in existing model-based optimization tools and propose a new approach that uses a novel VAE as its search model to overcome the problem. We demonstrate its advantage over prior methods in robustly finding improved samples, regardless of the imbalance and separation between low- and high-fitness samples. Our comprehensive benchmark on real and semi-synthetic protein datasets as well as solution design for physics-informed neural networks, showcases the generality of our approach in discrete and continuous design spaces. Our implementation is available at https://github.com/sabagh1994/PGVAE.
Authors: Jiarong Pan, Stefan Falkner, Felix Berkenkamp, Joaquin Vanschoren
Abstract: Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged as a way to leverage knowledge from related tasks to optimize new tasks faster. However, existing meta-learning BO methods rely on surrogate models that suffer from scalability issues and are sensitive to observations with different scales and noise types across tasks. Moreover, they often overlook the uncertainty associated with task similarity. This leads to unreliable task adaptation when only limited observations are obtained or when the new tasks differ significantly from the related tasks. To address these limitations, we propose a novel meta-learning BO approach that bypasses the surrogate model and directly learns the utility of queries across tasks. Our method explicitly models task uncertainty and includes an auxiliary model to enable robust adaptation to new tasks. Extensive experiments show that our method demonstrates strong anytime performance and outperforms state-of-the-art meta-learning BO methods in various benchmarks.
Authors: Hemn Barzan Abdalla, Awder Ahmed, Guoquan Li, Nasser Mustafa, Abdur Rashid Sangi
Abstract: Thalassemia is a heritable blood disorder which is the outcome of a genetic defect causing lack of production of hemoglobin polypeptide chains. However, there is less understanding of the precise frequency as well as sharing in these areas. Knowing about the frequency of thalassemia occurrence and dependable mutations is thus a significant step in preventing, controlling, and treatment planning. Here, Political Tangent Search Optimizer based Transfer Learning (PTSO_TL) is introduced for thalassemia detection. Initially, input data obtained from a particular dataset is normalized in the data normalization stage. Quantile normalization is utilized in the data normalization stage, and the data are then passed to the feature fusion phase, in which Weighted Euclidean Distance with Deep Maxout Network (DMN) is utilized. Thereafter, data augmentation is performed using the oversampling method to increase data dimensionality. Lastly, thalassemia detection is carried out by TL, wherein a convolutional neural network (CNN) is utilized with hyperparameters from a trained model such as Xception. TL is tuned by PTSO, and the training algorithm PTSO is presented by merging of Political Optimizer (PO) and Tangent Search Algorithm (TSA). Furthermore, PTSO_TL obtained maximal precision, recall, and f-measure values of about 94.3%, 96.1%, and 95.2%, respectively.
Authors: Shunta Maeda
Abstract: We propose a generative model termed Deciphering Autoencoders. In this model, we assign a unique random dropout pattern to each data point in the training dataset and then train an autoencoder to reconstruct the corresponding data point using this pattern as information to be encoded. Even if a completely random dropout pattern is assigned to each data point regardless of their similarities, a sufficiently large encoder can smoothly map them to a low-dimensional latent space to reconstruct individual training data points. During inference, using a dropout pattern different from those used during training allows the model to function as a generator. Since the training of Deciphering Autoencoders relies solely on reconstruction error, it offers more stable training compared to other generative models. Despite their simplicity, Deciphering Autoencoders show sampling quality comparable to DCGAN on the CIFAR-10 dataset.
Authors: T. Lucas Makinen, Justin Alsing, Benjamin D. Wandelt
Abstract: Set-based learning is an essential component of modern deep learning and network science. Graph Neural Networks (GNNs) and their edge-free counterparts Deepsets have proven remarkably useful on ragged and topologically challenging datasets. The key to learning informative embeddings for set members is a specified aggregation function, usually a sum, max, or mean. We propose Fishnets, an aggregation strategy for learning information-optimal embeddings for sets of data for both Bayesian inference and graph aggregation. We demonstrate that i) Fishnets neural summaries can be scaled optimally to an arbitrary number of data objects, ii) Fishnets aggregations are robust to changes in data distribution, unlike standard deepsets, iii) Fishnets saturate Bayesian information content and extend to regimes where MCMC techniques fail and iv) Fishnets can be used as a drop-in aggregation scheme within GNNs. We show that by adopting a Fishnets aggregation scheme for message passing, GNNs can achieve state-of-the-art performance versus architecture size on ogbn-protein data over existing benchmarks with a fraction of learnable parameters and faster training time.
Authors: Chengyao Wen, Yin Lou
Abstract: Rules are widely used in Fintech institutions to make fraud prevention decisions, since rules are highly interpretable thanks to their intuitive if-then structure. In practice, a two-stage framework of fraud prevention decision rule set mining is usually employed in large Fintech institutions; Stage 1 generates a potentially large pool of rules and Stage 2 aims to produce a refined rule subset according to some criteria (typically based on precision and recall). This paper focuses on improving the flexibility and efficacy of this two-stage framework, and is concerned with finding high-quality rule subsets in a bi-objective space (such as precision and recall). To this end, we first introduce a novel algorithm called SpectralRules that directly generates a compact pool of rules in Stage 1 with high diversity. We empirically find such diversity improves the quality of the final rule subset. In addition, we introduce an intermediate stage between Stage 1 and 2 that adopts the concept of Pareto optimality and aims to find a set of non-dominated rule subsets, which constitutes a Pareto front. This intermediate stage greatly simplifies the selection criteria and increases the flexibility of Stage 2. For this intermediate stage, we propose a heuristic-based framework called PORS and we identify that the core of PORS is the problem of solution selection on the front (SSF). We provide a systematic categorization of the SSF problem and a thorough empirical evaluation of various SSF methods on both public and proprietary datasets. On two real application scenarios within Alipay, we demonstrate the advantages of our proposed methodology over existing work.
Authors: Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande
Abstract: The advent of large language models (LLMs) has ushered in a new paradigm of search engines that use generative models to gather and summarize information to answer user queries. This emerging technology, which we formalize under the unified framework of generative engines (GEs), can generate accurate and personalized responses, rapidly replacing traditional search engines like Google and Bing. Generative Engines typically satisfy queries by synthesizing information from multiple sources and summarizing them using LLMs. While this shift significantly improves $\textit{user}$ utility and $\textit{generative search engine}$ traffic, it poses a huge challenge for the third stakeholder -- website and content creators. Given the black-box and fast-moving nature of generative engines, content creators have little to no control over $\textit{when}$ and $\textit{how}$ their content is displayed. With generative engines here to stay, we must ensure the creator economy is not disadvantaged. To address this, we introduce Generative Engine Optimization (GEO), the first novel paradigm to aid content creators in improving their content visibility in generative engine responses through a flexible black-box optimization framework for optimizing and defining visibility metrics. We facilitate systematic evaluation by introducing GEO-bench, a large-scale benchmark of diverse user queries across multiple domains, along with relevant web sources to answer these queries. Through rigorous evaluation, we demonstrate that GEO can boost visibility by up to $40\%$ in generative engine responses. Moreover, we show the efficacy of these strategies varies across domains, underscoring the need for domain-specific optimization methods. Our work opens a new frontier in information discovery systems, with profound implications for both developers of generative engines and content creators.
Authors: Alex Lewandowski, Haruto Tanaka, Dale Schuurmans, Marlos C. Machado
Abstract: Loss of plasticity is a phenomenon in which neural networks lose their ability to learn from new experience. Despite being empirically observed in several problem settings, little is understood about the mechanisms that lead to loss of plasticity. In this paper, we offer a consistent explanation for loss of plasticity: Neural networks lose directions of curvature during training and that loss of plasticity can be attributed to this reduction in curvature. To support such a claim, we provide a systematic investigation of loss of plasticity across continual learning tasks using MNIST, CIFAR-10 and ImageNet. Our findings illustrate that loss of curvature directions coincides with loss of plasticity, while also showing that previous explanations are insufficient to explain loss of plasticity in all settings. Lastly, we show that regularizers which mitigate loss of plasticity also preserve curvature, motivating a simple distributional regularizer that proves to be effective across the problem settings we considered.
Authors: Emma Cramer, Jonas Reiher, Sebastian Trimpe
Abstract: Reinforcement learning (RL) for robot control typically requires a detailed representation of the environment state, including information about task-relevant objects not directly measurable. Keypoint detectors, such as spatial autoencoders (SAEs), are a common approach to extracting a low-dimensional representation from high-dimensional image data. SAEs aim at spatial features such as object positions, which are often useful representations in robotic RL. However, whether an SAE is actually able to track objects in the scene and thus yields a spatial state representation well suited for RL tasks has rarely been examined due to a lack of established metrics. In this paper, we propose to assess the performance of an SAE instance by measuring how well keypoints track ground truth objects in images. We present a computationally lightweight metric and use it to evaluate common baseline SAE architectures on image data from a simulated robot task. We find that common SAEs differ substantially in their spatial extraction capability. Furthermore, we validate that SAEs that perform well in our metric achieve superior performance when used in downstream RL. Thus, our metric is an effective and lightweight indicator of RL performance before executing expensive RL training. Building on these insights, we identify three key modifications of SAE architectures to improve tracking performance. We make our code available at anonymous.4open.science/r/sae-rl.
Authors: Yin Li, Yu Xiong, Wenxin Fan, Kai Wang, Qingqing Yu, Liping Si, Patrick van der Smagt, Jun Tang, Nutan Chen
Abstract: Objective: Subcutaneous Immunotherapy (SCIT) is the long-lasting causal treatment of allergic rhinitis (AR). How to enhance the adherence of patients to maximize the benefit of allergen immunotherapy (AIT) plays a crucial role in the management of AIT. This study aims to leverage novel machine learning models to precisely predict the risk of non-adherence of AR patients and related local symptom scores in three years SCIT. Methods: The research develops and analyzes two models, sequential latent-variable model (SLVM) of Sequential Latent Actor-Critic (SLAC) and Long Short-Term Memory (LSTM) evaluating them based on scoring and adherence prediction capabilities. Results: Excluding the biased samples at the first time step, the predictive adherence accuracy of the SLAC models is from 60\% to 72\%, and for LSTM models, it is 66\% to 84\%, varying according to the time steps. The range of Root Mean Square Error (RMSE) for SLAC models is between 0.93 and 2.22, while for LSTM models it is between 1.09 and 1.77. Notably, these RMSEs are significantly lower than the random prediction error of 4.55. Conclusion: We creatively apply sequential models in the long-term management of SCIT with promising accuracy in the prediction of SCIT nonadherence in AR patients. While LSTM outperforms SLAC in adherence prediction, SLAC excels in score prediction for patients undergoing SCIT for AR. The state-action-based SLAC adds flexibility, presenting a novel and effective approach for managing long-term AIT.
Authors: YuQing Xie, Tess Smidt
Abstract: Equivariant neural networks (ENNs) have been shown to be extremely effective in applications involving underlying symmetries. By construction ENNs cannot produce lower symmetry outputs given a higher symmetry input. However, symmetry breaking occurs in many physical systems and we may obtain a less symmetric stable state from an initial highly symmetric one. Hence, it is imperative that we understand how to systematically break symmetry in ENNs. In this work, we propose a novel symmetry breaking framework that is fully equivariant and is the first which fully addresses spontaneous symmetry breaking. We emphasize that our approach is general and applicable to equivariance under any group. To achieve this, we introduce the idea of symmetry breaking sets (SBS). Rather than redesign existing networks, we design sets of symmetry breaking objects which we feed into our network based on the symmetry of our inputs and outputs. We show there is a natural way to define equivariance on these sets, which gives an additional constraint. Minimizing the size of these sets equates to data efficiency. We prove that minimizing these sets translates to a well studied group theory problem, and tabulate solutions to this problem for the point groups. Finally, we provide some examples of symmetry breaking to demonstrate how our approach works in practice.
Authors: Ayush Jain, Andrea Montanari, Eren Sasoglu
Abstract: Collecting large quantities of high-quality data can be prohibitively expensive or impractical, and a bottleneck in machine learning. One may instead augment a small set of $n$ data points from the target distribution with data from more accessible sources, e.g. data collected under different circumstances or synthesized by generative models. We refer to such data as `surrogate data.' We introduce a weighted empirical risk minimization (ERM) approach for integrating surrogate data into training. We analyze mathematically this method under several classical statistical models, and validate our findings empirically on datasets from different domains. Our main findings are: $(i)$ Integrating surrogate data can significantly reduce the test error on the original distribution. Surprisingly, this can happen even when the surrogate data is unrelated to the original ones. We trace back this behavior to the classical Stein's paradox. $(ii)$ In order to reap the benefit of surrogate data, it is crucial to use optimally weighted ERM. $(iii)$ The test error of models trained on mixtures of real and surrogate data is approximately described by a scaling law. This scaling law can be used to predict the optimal weighting scheme, and to choose the amount of surrogate data to add.
Authors: Maksim Sinelnikov, Manuel Haussmann, Harri L\"ahdesm\"aki
Abstract: Longitudinal data are important in numerous fields, such as healthcare, sociology and seismology, but real-world datasets present notable challenges for practitioners because they can be high-dimensional, contain structured missingness patterns, and measurement time points can be governed by an unknown stochastic process. While various solutions have been suggested, the majority of them have been designed to account for only one of these challenges. In this work, we propose a flexible and efficient latent-variable model that is capable of addressing all these limitations. Our approach utilizes Gaussian processes to capture temporal correlations between samples and their associated missingness masks as well as to model the underlying point process. We construct our model as a variational autoencoder together with deep neural network parameterised encoder and decoder models, and develop a scalable amortised variational inference approach for efficient model training. We demonstrate competitive performance using both simulated and real datasets.
Authors: Taojie Kuang, Pengfei Liu, Zhixiang Ren
Abstract: The precise prediction of molecular properties is essential for advancements in drug development, particularly in virtual screening and compound optimization. The recent introduction of numerous deep learning-based methods has shown remarkable potential in enhancing molecular property prediction (MPP), especially improving accuracy and insights into molecular structures. Yet, two critical questions arise: does the integration of domain knowledge augment the accuracy of molecular property prediction and does employing multi-modal data fusion yield more precise results than unique data source methods? To explore these matters, we comprehensively review and quantitatively analyze recent deep learning methods based on various benchmarks. We discover that integrating molecular information significantly improves molecular property prediction (MPP) for both regression and classification tasks. Specifically, regression improvements, measured by reductions in root mean square error (RMSE), are up to 4.0%, while classification enhancements, measured by the area under the receiver operating characteristic curve (ROC-AUC), are up to 1.7%. We also discover that enriching 2D graphs with 1D SMILES boosts multi-modal learning performance for regression tasks by up to 9.1%, and augmenting 2D graphs with 3D information increases performance for classification tasks by up to 13.2%, with both enhancements measured using ROC-AUC. The two consolidated insights offer crucial guidance for future advancements in drug discovery.
Authors: William Muldrew, Peter Hayes, Mingtian Zhang, David Barber
Abstract: As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model resources in the case where LLMs themselves are used as oracles. Reinforcement learning from Human or AI preferences (RLHF/RLAIF) is the most prominent example of such a technique, but is complex and often unstable. Direct Preference Optimization (DPO) has recently been proposed as a simpler and more stable alternative. In this work, we develop an active learning strategy for DPO to make better use of preference labels. We propose a practical acquisition function for prompt/completion pairs based on the predictive entropy of the language model and a measure of certainty of the implicit preference model optimized by DPO. We demonstrate how our approach improves both the rate of learning and final performance of fine-tuning on pairwise preference data.
Authors: Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur Muhammad Mahi Shafiullah, Lerrel Pinto
Abstract: Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision making. Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction. A recent class of models called Behavior Transformers (BeT) addresses this by discretizing actions using k-means clustering to capture different modes. However, k-means struggles to scale for high-dimensional action spaces or long sequences, and lacks gradient information, and thus BeT suffers in modeling long-range actions. In this work, we present Vector-Quantized Behavior Transformer (VQ-BeT), a versatile model for behavior generation that handles multimodal action prediction, conditional generation, and partial observations. VQ-BeT augments BeT by tokenizing continuous actions with a hierarchical vector quantization module. Across seven environments including simulated manipulation, autonomous driving, and robotics, VQ-BeT improves on state-of-the-art models such as BeT and Diffusion Policies. Importantly, we demonstrate VQ-BeT's improved ability to capture behavior modes while accelerating inference speed 5x over Diffusion Policies. Videos and code can be found https://sjlee.cc/vq-bet
URLs: https://sjlee.cc/vq-bet
Authors: Yudong Luo, Yangchen Pan, Han Wang, Philip Torr, Pascal Poupart
Abstract: Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications. This inefficiency stems from two main facts: a focus on tail-end performance that overlooks many sampled trajectories, and the potential of gradient vanishing when the lower tail of the return distribution is overly flat. To address these challenges, we propose a simple mixture policy parameterization. This method integrates a risk-neutral policy with an adjustable policy to form a risk-averse policy. By employing this strategy, all collected trajectories can be utilized for policy updating, and the issue of vanishing gradients is counteracted by stimulating higher returns through the risk-neutral component, thus lifting the tail and preventing flatness. Our empirical study reveals that this mixture parameterization is uniquely effective across a variety of benchmark domains. Specifically, it excels in identifying risk-averse CVaR policies in some Mujoco environments where the traditional CVaR-PG fails to learn a reasonable policy.
Authors: Justin N. Kreikemeyer, Philipp Andelfinger, Adelinde M. Uhrmacher
Abstract: Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters but also a suitable model structure. Recent work on the discovery of dynamical systems formulates this problem as a linear equation system. Here, we explore several simulation-based optimization approaches, which allow much greater freedom in the objective formulation and weaker conditions on the available data. We show that even for relatively small stochastic population models, simultaneous estimation of parameters and structure poses major challenges for optimization procedures. Particularly, we investigate the application of the local stochastic gradient descent method, commonly used for training machine learning models. We demonstrate accurate estimation of models but find that enforcing the inference of parsimonious, interpretable models drastically increases the difficulty. We give an outlook on how this challenge can be overcome.
Authors: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Abstract: A common issue in learning decision-making policies in data-rich settings is spurious correlations in the offline dataset, which can be caused by hidden confounders. Instrumental variable (IV) regression, which utilises a key unconfounded variable known as the instrument, is a standard technique for learning causal relationships between confounded action, outcome, and context variables. Most recent IV regression algorithms use a two-stage approach, where a deep neural network (DNN) estimator learnt in the first stage is directly plugged into the second stage, in which another DNN is used to estimate the causal effect. Naively plugging the estimator can cause heavy bias in the second stage, especially when regularisation bias is present in the first stage estimator. We propose DML-IV, a non-linear IV regression method that reduces the bias in two-stage IV regressions and effectively learns high-performing policies. We derive a novel learning objective to reduce bias and design the DML-IV algorithm following the double/debiased machine learning (DML) framework. The learnt DML-IV estimator has strong convergence rate and $O(N^{-1/2})$ suboptimality guarantees that match those when the dataset is unconfounded. DML-IV outperforms state-of-the-art IV regression methods on IV regression benchmarks and learns high-performing policies in the presence of instruments.
Authors: Huy V. Vo, Vasil Khalidov, Timoth\'ee Darcet, Th\'eo Moutakanni, Nikita Smetanin, Marc Szafraniec, Hugo Touvron, Camille Couprie, Maxime Oquab, Armand Joulin, Herv\'e J\'egou, Patrick Labatut, Piotr Bojanowski
Abstract: Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some limitations similar to those encountered in supervised learning, e.g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size. In this work, we consider the problem of automatic curation of high-quality datasets for self-supervised pre-training. We posit that such datasets should be large, diverse and balanced, and propose a clustering-based approach for building ones satisfying all these criteria. Our method involves successive and hierarchical applications of $k$-means on a large and diverse data repository to obtain clusters that distribute uniformly among data concepts, followed by a hierarchical, balanced sampling step from these clusters. Extensive experiments on three different data domains including web-based images, satellite images and text show that features trained on our automatically curated datasets outperform those trained on uncurated data while being on par or better than ones trained on manually curated data. Code is available at https://github.com/facebookresearch/ssl-data-curation.
URLs: https://github.com/facebookresearch/ssl-data-curation.
Authors: Jiayan Guo, Yusen Huo, Zhilin Zhang, Tianyu Wang, Chuan Yu, Jian Xu, Yan Zhang, Bo Zheng
Abstract: Auto-bidding plays a crucial role in facilitating online advertising by automatically providing bids for advertisers. Reinforcement learning (RL) has gained popularity for auto-bidding. However, most current RL auto-bidding methods are modeled through the Markovian Decision Process (MDP), which assumes the Markovian state transition. This assumption restricts the ability to perform in long horizon scenarios and makes the model unstable when dealing with highly random online advertising environments. To tackle this issue, this paper introduces AI-Generated Bidding (AIGB), a novel paradigm for auto-bidding through generative modeling. In this paradigm, we propose DiffBid, a conditional diffusion modeling approach for bid generation. DiffBid directly models the correlation between the return and the entire trajectory, effectively avoiding error propagation across time steps in long horizons. Additionally, DiffBid offers a versatile approach for generating trajectories that maximize given targets while adhering to specific constraints. Extensive experiments conducted on the real-world dataset and online A/B test on Alibaba advertising platform demonstrate the effectiveness of DiffBid, achieving 2.81% increase in GMV and 3.36% increase in ROI.
Authors: Zitao Song, Chao Yang, Chaojie Wang, Bo An, Shuang Li
Abstract: Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug-and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence. Built on the temporal point process model for events, our method employs the likelihood function as a score to evaluate generated logic trees. We propose an amortized Expectation-Maximization (EM) learning framework and treat the logic tree as latent variables. In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences. LLM provides a high-quality prior for the latent logic trees, however, since the posterior is built over a discrete combinatorial space, we cannot get the closed-form solution. We propose to generate logic tree samples from the posterior using a learnable GFlowNet, which is a diversity-seeking generator for structured discrete variables. The M-step employs the generated logic rules to approximate marginalization over the posterior, facilitating the learning of model parameters and refining the tunable LLM prior parameters. In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations. Empirical demonstrations showcase the promising performance and adaptability of our framework.
Authors: Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach
Abstract: Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc explanations, which may not suffice in high-stakes scenarios where transparency is crucial. In this paper, we present a GNN that is interpretable by design. Our model, Graph Neural Additive Network (GNAN), is a novel extension of the interpretable class of Generalized Additive Models, and can be visualized and fully understood by humans. GNAN is designed to be fully interpretable, allowing both global and local explanations at the feature and graph levels through direct visualization of the model. These visualizations describe the exact way the model uses the relationships between the target variable, the features, and the graph. We demonstrate the intelligibility of GNANs in a series of examples on different tasks and datasets. In addition, we show that the accuracy of GNAN is on par with black-box GNNs, making it suitable for critical applications where transparency is essential, alongside high accuracy.
Authors: Vignesh Kothapalli, Tom Tirer
Abstract: Recently, a vast amount of literature has focused on the "Neural Collapse" (NC) phenomenon, which emerges when training neural network (NN) classifiers beyond the zero training error point. The core component of NC is the decrease in the within class variability of the network's deepest features, dubbed as NC1. The theoretical works that study NC are typically based on simplified unconstrained features models (UFMs) that mask any effect of the data on the extent of collapse. In this paper, we provide a kernel-based analysis that does not suffer from this limitation. First, given a kernel function, we establish expressions for the traces of the within- and between-class covariance matrices of the samples' features (and consequently an NC1 metric). Then, we turn to focus on kernels associated with shallow NNs. First, we consider the NN Gaussian Process kernel (NNGP), associated with the network at initialization, and the complement Neural Tangent Kernel (NTK), associated with its training in the "lazy regime". Interestingly, we show that the NTK does not represent more collapsed features than the NNGP for prototypical data models. As NC emerges from training, we then consider an alternative to NTK: the recently proposed adaptive kernel, which generalizes NNGP to model the feature mapping learned from the training data. Contrasting our NC1 analysis for these two kernels enables gaining insights into the effect of data distribution on the extent of collapse, which are empirically aligned with the behavior observed with practical training of NNs.
Authors: Bruno Machado Pacheco, Eduardo Camponogara
Abstract: This paper introduces Physics-Informed Deep Equilibrium Models (PIDEQs) for solving initial value problems (IVPs) of ordinary differential equations (ODEs). Leveraging recent advancements in deep equilibrium models (DEQs) and physics-informed neural networks (PINNs), PIDEQs combine the implicit output representation of DEQs with physics-informed training techniques. We validate PIDEQs using the Van der Pol oscillator as a benchmark problem, demonstrating their efficiency and effectiveness in solving IVPs. Our analysis includes key hyperparameter considerations for optimizing PIDEQ performance. By bridging deep learning and physics-based modeling, this work advances computational techniques for solving IVPs, with implications for scientific computing and engineering applications.
Authors: Zongyue Qin, Yunsheng Bai, Atefeh Sohrabizadeh, Zijian Ding, Ziniu Hu, Yizhou Sun, Jason Cong
Abstract: In recent years, domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. To facilitate DSA designs, programmers use high-level synthesis (HLS) to compile a high-level description written in C/C++ into a design with low-level hardware description languages that eventually synthesize DSAs on circuits. However, creating a high-quality HLS design still demands significant domain knowledge, particularly in microarchitecture decisions expressed as \textit{pragmas}. Thus, it is desirable to automate such decisions with the help of machine learning for predicting the quality of HLS designs, requiring a deeper understanding of the program that consists of original code and pragmas. Naturally, these programs can be considered as sequence data. In addition, these programs can be compiled and converted into a control data flow graph (CDFG). But existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG, a model that allows interaction between the source code sequence modality and the graph modality in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results show that ProgSG reduces the RMSE of design performance predictions by up to $22\%$, and identifies designs with an average of $1.10\times$ and $1.26\times$ (up to $8.17\times$ and $13.31\times$) performance improvement in design space exploration (DSE) task compared to HARP and AutoDSE, respectively.
Authors: Ying Zhang, Peng Zhang, Mincong Huang, Jingyang Xiang, Yujie Wang, Chao Wang, Yineng Zhang, Lei Yu, Chuan Liu, Wei Lin
Abstract: Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding stages of inference. W4A8 is a promising strategy to accelerate both of them while usually leads to a significant performance degradation. To address these issues, we present QQQ, a Quality Quattuor-bit Quantization method with 4-bit weights and 8-bit activations. QQQ employs adaptive smoothing and Hessian-based compensation, significantly enhancing the performance of quantized models without extensive training. Furthermore, we meticulously engineer W4A8 GEMM kernels to increase inference speed. Our specialized per-channel W4A8 GEMM and per-group W4A8 GEMM achieve impressive speed increases of 3.67$\times$ and 3.29 $\times$ over FP16 GEMM. Our extensive experiments show that QQQ achieves performance on par with existing state-of-the-art LLM quantization methods while significantly accelerating inference, achieving speed boosts up to 2.24 $\times$, 2.10$\times$, and 1.25$\times$ compared to FP16, W8A8, and W4A16, respectively.
Authors: Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
Abstract: Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on data generated by humans, we may not expect the artificial model to outperform the humans on their original objectives. In this work, we study the phenomenon of transcendence: when a generative model achieves capabilities that surpass the abilities of the experts generating its data. We demonstrate transcendence by training an autoregressive transformer to play chess from game transcripts, and show that the trained model can sometimes achieve better performance than all players in the dataset. We theoretically prove that transcendence can be enabled by low-temperature sampling, and rigorously assess this claim experimentally. Finally, we discuss other sources of transcendence, laying the groundwork for future investigation of this phenomenon in a broader setting.
Authors: Chi Ma, Mincong Huang, Chao Wang, Yujie Wang, Lei Yu
Abstract: Massive Over-activation Yielded Uplifts(MOYU) is an inherent property of large language models, and dynamic activation(DA) based on the MOYU property is a clever yet under-explored strategy designed to accelerate inference in these models. Existing methods that utilize MOYU often face a significant 'Impossible Trinity': struggling to simultaneously maintain model performance, enhance inference speed, and extend applicability across various architectures. Due to the theoretical ambiguities surrounding MOYU, this paper elucidates the root cause of the MOYU property and outlines the mechanisms behind two primary limitations encountered by current DA methods: 1) history-related activation uncertainty, and 2) semantic-irrelevant activation inertia. Our analysis not only underscores the limitations of current dynamic activation strategies within large-scale LLaMA models but also proposes opportunities for refining the design of future sparsity schemes.
Authors: Massimiliano Lupo Pasini, Jong Youl Choi, Kshitij Mehta, Pei Zhang, David Rogers, Jonghyun Bae, Khaled Z. Ibrahim, Ashwin M. Aji, Karl W. Schulz, Jorda Polo, Prasanna Balaprakash
Abstract: We present our work on developing and training scalable graph foundation models (GFM) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFM training to tens of thousands of GPUs on datasets that consist of hundreds of millions of graphs. Our GFMs use multi-task learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as the total energy and atomic forces. Using over 150 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two United States Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge National Laboratory. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2,000 GPUs on Perlmutter and 16,000 GPUs on Frontier. Hyperparameter optimization (HPO) was performed on over 64,000 GPUs on Frontier to select GFM architectures with high accuracy. Early stopping was applied on each GFM architecture for energy awareness in performing such an extreme-scale task. The training of an ensemble of highest-ranked GFM architectures continued until convergence to establish uncertainty quantification (UQ) capabilities with ensemble learning. Our contribution opens the door for rapidly developing, training, and deploying GFMs using large-scale computational resources to enable AI-accelerated materials discovery and design.
Authors: Mengdan Zhu, Raasikh Kanjiani, Jiahui Lu, Andrew Choi, Qirui Ye, Liang Zhao
Abstract: Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in interpreting machine learning models, understanding latent variables in generative models remains challenging. This paper introduces LatentExplainer, a framework for automatically generating semantically meaningful explanations of latent variables in deep generative models. LatentExplainer tackles three main challenges: inferring the meaning of latent variables, aligning explanations with inductive biases, and handling varying degrees of explainability. By perturbing latent variables and interpreting changes in generated data, the framework provides a systematic approach to understanding and controlling the data generation process, enhancing the transparency and interpretability of deep generative models. We evaluate our proposed method on several real-world and synthetic datasets, and the results demonstrate superior performance in generating high-quality explanations of latent variables.
Authors: Parisa Davar, Fr\'ed\'eric Godin, Jose Garrido
Abstract: This paper tackles the problem of mitigating catastrophic risk (which is risk with very low frequency but very high severity) in the context of a sequential decision making process. This problem is particularly challenging due to the scarcity of observations in the far tail of the distribution of cumulative costs (negative rewards). A policy gradient algorithm is developed, that we call POTPG. It is based on approximations of the tail risk derived from extreme value theory. Numerical experiments highlight the out-performance of our method over common benchmarks, relying on the empirical distribution. An application to financial risk management, more precisely to the dynamic hedging of a financial option, is presented.
Authors: Mahdi Mohammadizadeh, Arash Mozhdehi, Yani Ioannou, Xin Wang
Abstract: Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be biased towards the majority class(es). Conventional methods typically tackle this problem through the assignment of weights to each one of the class samples based on a function of their loss, which can lead to over-fitting on outliers. In this paper, we propose a meta-learning algorithm, named Meta-GCN, for adaptively learning the example weights by simultaneously minimizing the unbiased meta-data set loss and optimizing the model weights through the use of a small unbiased meta-data set. Through experiments, we have shown that Meta-GCN outperforms state-of-the-art frameworks and other baselines in terms of accuracy, the area under the receiver operating characteristic (AUC-ROC) curve, and macro F1-Score for classification tasks on two different datasets.
Authors: Yiqiao Jin, Andrew Zhao, Yeon-Chang Lee, Meng Ye, Ajay Divakaran, Srijan Kumar
Abstract: We developed DyGETViz, a novel framework for effectively visualizing dynamic graphs (DGs) that are ubiquitous across diverse real-world systems. This framework leverages recent advancements in discrete-time dynamic graph (DTDG) models to adeptly handle the temporal dynamics inherent in dynamic graphs. DyGETViz effectively captures both micro- and macro-level structural shifts within these graphs, offering a robust method for representing complex and massive dynamic graphs. The application of DyGETViz extends to a diverse array of domains, including ethology, epidemiology, finance, genetics, linguistics, communication studies, social studies, and international relations. Through its implementation, DyGETViz has revealed or confirmed various critical insights. These include the diversity of content sharing patterns and the degree of specialization within online communities, the chronological evolution of lexicons across decades, and the distinct trajectories exhibited by aging-related and non-related genes. Importantly, DyGETViz enhances the accessibility of scientific findings to non-domain experts by simplifying the complexities of dynamic graphs. Our framework is released as an open-source Python package for use across diverse disciplines. Our work not only addresses the ongoing challenges in visualizing and analyzing DTDG models but also establishes a foundational framework for future investigations into dynamic graph representation and analysis across various disciplines.
Authors: Zhenqiao Song, Lei Li
Abstract: Designing protein sequences with desired biological function is crucial in biology and chemistry. Recent machine learning methods use a surrogate sequence-function model to replace the expensive wet-lab validation. How can we efficiently generate diverse and novel protein sequences with high fitness? In this paper, we propose IsEM-Pro, an approach to generate protein sequences towards a given fitness criterion. At its core, IsEM-Pro is a latent generative model, augmented by combinatorial structure features from a separately learned Markov random fields (MRFs). We develop an Monte Carlo Expectation-Maximization method (MCEM) to learn the model. During inference, sampling from its latent space enhances diversity while its MRFs features guide the exploration in high fitness regions. Experiments on eight protein sequence design tasks show that our IsEM-Pro outperforms the previous best methods by at least 55% on average fitness score and generates more diverse and novel protein sequences.
Authors: Norbert Tihanyi, Ridhi Jain, Yiannis Charalambous, Mohamed Amine Ferrag, Youcheng Sun, Lucas C. Cordeiro
Abstract: This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify vulnerabilities and extract counterexamples. These counterexamples are supported by mathematical proofs and the stack trace of the vulnerabilities. Using a specially designed prompt, we combine the original source code with the identified vulnerability, including its stack trace and counterexample that specifies the line number and error type. This combined information is then fed into an LLM, which is instructed to attempt to fix the code. The new code is subsequently verified again using BMC to ensure the fix succeeded. We present the ESBMC-AI framework as a proof of concept, leveraging the well-recognized and industry-adopted Efficient SMT-based Context-Bounded Model Checker (ESBMC) and a pre-trained transformer model to detect and fix errors in C programs, particularly in critical software components. We evaluated our approach on 50,000 C programs randomly selected from the FormAI dataset with their respective vulnerability classifications. Our results demonstrate ESBMC-AI's capability to automate the detection and repair of issues such as buffer overflow, arithmetic overflow, and pointer dereference failures with high accuracy. ESBMC-AI is a pioneering initiative, integrating LLMs with BMC techniques, offering potential integration into the continuous integration and deployment (CI/CD) process within the software development lifecycle.
Authors: Patrick Benjamin, Alessandro Abate
Abstract: We introduce networked communication to the mean-field game framework, in particular to oracle-free settings where $N$ decentralised agents learn along a single, non-episodic run of the empirical system. We prove that our architecture, with only a few reasonable assumptions about network structure, has sample guarantees bounded between those of the centralised- and independent-learning cases. We discuss how the sample guarantees of the three theoretical algorithms do not actually result in practical convergence. We therefore show that in practical settings where the theoretical parameters are not observed (leading to poor estimation of the Q-function), our communication scheme significantly accelerates convergence over the independent case (and often even the centralised case), without relying on the assumption of a centralised learner. We contribute further practical enhancements to all three theoretical algorithms, allowing us to present their first empirical demonstrations. Our experiments confirm that we can remove several of the theoretical assumptions of the algorithms, and display the empirical convergence benefits brought by our new networked communication. We additionally show that the networked approach has significant advantages, over both the centralised and independent alternatives, in terms of robustness to unexpected learning failures and to changes in population size.
Authors: Xiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu, Jieyu Zhang, Satyen Subramaniam, Arjun R. Loomba, Shichang Zhang, Yizhou Sun, Wei Wang
Abstract: Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that the current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.
Authors: Weihao Lu, Haobo Zhang, Yicheng Li, Manyun Xu, Qian Lin
Abstract: We perform a study on kernel regression for large-dimensional data (where the sample size $n$ is polynomially depending on the dimension $d$ of the samples, i.e., $n\asymp d^{\gamma}$ for some $\gamma >0$ ). We first build a general tool to characterize the upper bound and the minimax lower bound of kernel regression for large dimensional data through the Mendelson complexity $\varepsilon_{n}^{2}$ and the metric entropy $\bar{\varepsilon}_{n}^{2}$ respectively. When the target function falls into the RKHS associated with a (general) inner product model defined on $\mathbb{S}^{d}$, we utilize the new tool to show that the minimax rate of the excess risk of kernel regression is $n^{-1/2}$ when $n\asymp d^{\gamma}$ for $\gamma =2, 4, 6, 8, \cdots$. We then further determine the optimal rate of the excess risk of kernel regression for all the $\gamma>0$ and find that the curve of optimal rate varying along $\gamma$ exhibits several new phenomena including the multiple descent behavior and the periodic plateau behavior. As an application, For the neural tangent kernel (NTK), we also provide a similar explicit description of the curve of optimal rate. As a direct corollary, we know these claims hold for wide neural networks as well.
Authors: Nishchal Prasad, Mohand Boughanem, Taoufik Dkaki
Abstract: Automatic legal judgment prediction and its explanation suffer from the problem of long case documents exceeding tens of thousands of words, in general, and having a non-uniform structure. Predicting judgments from such documents and extracting their explanation becomes a challenging task, more so on documents with no structural annotation. We define this problem as "scarce annotated legal documents" and explore their lack of structural information and their long lengths with a deep-learning-based classification framework which we call MESc; "Multi-stage Encoder-based Supervised with-clustering"; for judgment prediction. We explore the adaptability of LLMs with multi-billion parameters (GPT-Neo, and GPT-J) to legal texts and their intra-domain(legal) transfer learning capacity. Alongside this, we compare their performance and adaptability with MESc and the impact of combining embeddings from their last layers. For such hierarchical models, we also propose an explanation extraction algorithm named ORSE; Occlusion sensitivity-based Relevant Sentence Extractor; based on the input-occlusion sensitivity of the model, to explain the predictions with the most relevant sentences from the document. We explore these methods and test their effectiveness with extensive experiments and ablation studies on legal documents from India, the European Union, and the United States with the ILDC dataset and a subset of the LexGLUE dataset. MESc achieves a minimum total performance gain of approximately 2 points over previous state-of-the-art proposed methods, while ORSE applied on MESc achieves a total average gain of 50% over the baseline explainability scores.
Authors: Taojie Kuang, Yiming Ren, Zhixiang Ren
Abstract: Molecular property prediction, crucial for early drug candidate screening and optimization, has seen advancements with deep learning-based methods. While deep learning-based methods have advanced considerably, they often fall short in fully leveraging 3D spatial information. Specifically, current molecular encoding techniques tend to inadequately extract spatial information, leading to ambiguous representations where a single one might represent multiple distinct molecules. Moreover, existing molecular modeling methods focus predominantly on the most stable 3D conformations, neglecting other viable conformations present in reality. To address these issues, we propose 3D-Mol, a novel approach designed for more accurate spatial structure representation. It deconstructs molecules into three hierarchical graphs to better extract geometric information. Additionally, 3D-Mol leverages contrastive learning for pretraining on 20 million unlabeled data, treating their conformations with identical topological structures as weighted positive pairs and contrasting ones as negatives, based on the similarity of their 3D conformation descriptors and fingerprints. We compare 3D-Mol with various state-of-the-art baselines on 7 benchmarks and demonstrate our outstanding performance.
Authors: Tob\'ias I. Liaudat, Matthijs Mars, Matthew A. Price, Marcelo Pereyra, Marta M. Betcke, Jason D. McEwen
Abstract: Next-generation radio interferometers like the Square Kilometer Array have the potential to unlock scientific discoveries thanks to their unprecedented angular resolution and sensitivity. One key to unlocking their potential resides in handling the deluge and complexity of incoming data. This challenge requires building radio interferometric imaging methods that can cope with the massive data sizes and provide high-quality image reconstructions with uncertainty quantification (UQ). This work proposes a method coined QuantifAI to address UQ in radio-interferometric imaging with data-driven (learned) priors for high-dimensional settings. Our model, rooted in the Bayesian framework, uses a physically motivated model for the likelihood. The model exploits a data-driven convex prior, which can encode complex information learned implicitly from simulations and guarantee the log-concavity of the posterior. We leverage probability concentration phenomena of high-dimensional log-concave posteriors that let us obtain information about the posterior, avoiding MCMC sampling techniques. We rely on convex optimisation methods to compute the MAP estimation, which is known to be faster and better scale with dimension than MCMC sampling strategies. Our method allows us to compute local credible intervals, i.e., Bayesian error bars, and perform hypothesis testing of structure on the reconstructed image. In addition, we propose a novel blazing-fast method to compute pixel-wise uncertainties at different scales. We demonstrate our method by reconstructing radio-interferometric images in a simulated setting and carrying out fast and scalable UQ, which we validate with MCMC sampling. Our method shows an improved image quality and more meaningful uncertainties than the benchmark method based on a sparsity-promoting prior. QuantifAI's source code: https://github.com/astro-informatics/QuantifAI.
Authors: Vladimir Arkhipkin, Andrei Filatov, Viacheslav Vasilev, Anastasia Maltseva, Said Azizov, Igor Pavlov, Julia Agafonova, Andrey Kuznetsov, Denis Dimitrov
Abstract: We present Kandinsky 3.0, a large-scale text-to-image generation model based on latent diffusion, continuing the series of text-to-image Kandinsky models and reflecting our progress to achieve higher quality and realism of image generation. In this report we describe the architecture of the model, the data collection procedure, the training technique, and the production system for user interaction. We focus on the key components that, as we have identified as a result of a large number of experiments, had the most significant impact on improving the quality of our model compared to the others. We also describe extensions and applications of our model, including super resolution, inpainting, image editing, image-to-video generation, and a distilled version of Kandinsky 3.0 - Kandinsky 3.1, which does inference in 4 steps of the reverse process and 20 times faster without visual quality decrease. By side-by-side human preferences comparison, Kandinsky becomes better in text understanding and works better on specific domains. The code is available at https://github.com/ai-forever/Kandinsky-3
Authors: Daniel Gomes de Pinho Zanco, Leszek Szczecinski, Jacob Benesty
Abstract: In this work, we consider the problem of regularization in the design of minimum mean square error (MMSE) linear filters. Using the relationship with statistical machine learning methods, using a Bayesian approach, the regularization parameter is found from the observed signals in a simple and automatic manner. The proposed approach is illustrated in system identification and beamforming examples, where the automatic regularization is shown to yield near-optimal results.
Authors: Fran\c{c}ois Portier, Lionel Truquet, Ikko Yamane
Abstract: Many existing covariate shift adaptation methods estimate sample weights given to loss values to mitigate the gap between the source and the target distribution. However, estimating the optimal weights typically involves computationally expensive matrix inversion and hyper-parameter tuning. In this paper, we propose a new covariate shift adaptation method which avoids estimating the weights. The basic idea is to directly work on unlabeled target data, labeled according to the $k$-nearest neighbors in the source dataset. Our analysis reveals that setting $k = 1$ is an optimal choice. This property removes the necessity of tuning the only hyper-parameter $k$ and leads to a running time quasi-linear in the sample size. Our results include sharp rates of convergence for our estimator, with a tight control of the mean square error and explicit constants. In particular, the variance of our estimators has the same rate of convergence as for standard parametric estimation despite their non-parametric nature. The proposed estimator shares similarities with some matching-based treatment effect estimators used, e.g., in biostatistics, econometrics, and epidemiology. Our experiments show that it achieves drastic reduction in the running time with remarkable accuracy.
Authors: Jiayuan Chen, You Shi, Changyan Yi, Hongyang Du, Jiawen Kang, Dusit Niyato
Abstract: The Internet of things (IoT) can significantly enhance the quality of human life, specifically in healthcare, attracting extensive attentions to IoT-healthcare services. Meanwhile, the human digital twin (HDT) is proposed as an innovative paradigm that can comprehensively characterize the replication of the individual human body in the digital world and reflect its physical status in real time. Naturally, HDT is envisioned to empower IoT-healthcare beyond the application of healthcare monitoring by acting as a versatile and vivid human digital testbed, simulating the outcomes and guiding the practical treatments. However, successfully establishing HDT requires high-fidelity virtual modeling and strong information interactions but possibly with scarce, biased and noisy data. Fortunately, a recent popular technology called generative artificial intelligence (GAI) may be a promising solution because it can leverage advanced AI algorithms to automatically create, manipulate, and modify valuable while diverse data. This survey particularly focuses on the implementation of GAI-driven HDT in IoT-healthcare. We start by introducing the background of IoT-healthcare and the potential of GAI-driven HDT. Then, we delve into the fundamental techniques and present the overall framework of GAI-driven HDT. After that, we explore the realization of GAI-driven HDT in detail, including GAI-enabled data acquisition, communication, data management, digital modeling, and data analysis. Besides, we discuss typical IoT-healthcare applications that can be revolutionized by GAI-driven HDT, namely personalized health monitoring and diagnosis, personalized prescription, and personalized rehabilitation. Finally, we conclude this survey by highlighting some future research directions.
Authors: Yizhak Elboher, Raya Elsaleh, Omri Isac, M\'elanie Ducoffe, Audrey Galametz, Guillaume Pov\'eda, Ryma Boumazouza, No\'emie Cohen, Guy Katz
Abstract: As deep neural networks (DNNs) are becoming the prominent solution for many computational problems, the aviation industry seeks to explore their potential in alleviating pilot workload and in improving operational safety. However, the use of DNNs in this type of safety-critical applications requires a thorough certification process. This need can be addressed through formal verification, which provides rigorous assurances -- e.g.,~by proving the absence of certain mispredictions. In this case-study paper, we demonstrate this process using an image-classifier DNN currently under development at Airbus and intended for use during the aircraft taxiing phase. We use formal methods to assess this DNN's robustness to three common image perturbation types: noise, brightness and contrast, and some of their combinations. This process entails multiple invocations of the underlying verifier, which might be computationally expensive; and we therefore propose a method that leverages the monotonicity of these robustness properties, as well as the results of past verification queries, in order to reduce the overall number of verification queries required by nearly 60%. Our results provide an indication of the level of robustness achieved by the DNN classifier under study, and indicate that it is considerably more vulnerable to noise than to brightness or contrast perturbations.
Authors: Bhabesh Mali, Karthik Maddala, Vatsal Gupta, Sweeya Reddy, Chandan Karfa, Ramesh Karri
Abstract: System Verilog Assertion (SVA) formulation -- a critical yet complex task is a prerequisite in the Assertion Based Verification (ABV) process. Traditionally, SVA formulation involves expert-driven interpretation of specifications, which is time-consuming and prone to human error. Recently, LLM-informed automatic assertion generation is gaining interest. We designed a novel framework called ChIRAAG, based on OpenAI GPT4, to generate SVA from natural language specifications of a design. ChIRAAG constitutes the systematic breakdown of design specifications into a standardized format, further generating assertions from formatted specifications using LLM. Furthermore, we used few test cases to validate the LLM-generated assertions. Automatic feedback of log messages from the simulation tool to the LLM ensures that the framework can generate correct SVAs. In our experiments, only 27% of LLM-generated raw assertions had errors, which was rectified in few iterations based on the simulation log. Our results on OpenTitan designs show that LLMs can streamline and assist engineers in the assertion generation process, reshaping verification workflows.
Authors: Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, Zheng Liu
Abstract: In this paper, we present a new embedding model, called M3-Embedding, which is distinguished for its versatility in Multi-Linguality, Multi-Functionality, and Multi-Granularity. It can support more than 100 working languages, leading to new state-of-the-art performances on multi-lingual and cross-lingual retrieval tasks. It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval, which provides a unified model foundation for real-world IR applications. It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. The effective training of M3-Embedding involves the following technical contributions. We propose a novel self-knowledge distillation approach, where the relevance scores from different retrieval functionalities can be integrated as the teacher signal to enhance the training quality. We also optimize the batching strategy, enabling a large batch size and high training throughput to ensure the discriminativeness of embeddings. To the best of our knowledge, M3-Embedding is the first embedding model which realizes such a strong versatility. The model and code will be publicly available at https://github.com/FlagOpen/FlagEmbedding.
Authors: Claudionor N. Coelho Jr, Hanchen Xiong, Tushar Karayil, Sree Koratala, Rex Shang, Jacob Bollinger, Mohamed Shabar, Syam Nair
Abstract: The advancement of Large Language Models (LLM) has also resulted in an equivalent proliferation in its applications. Software design, being one, has gained tremendous benefits in using LLMs as an interface component that extends fixed user stories. However, inclusion of LLM-based AI agents in software design often poses unexpected challenges, especially in the estimation of development efforts. Through the example of UI-based user stories, we provide a comparison against traditional methods and propose a new way to enhance specifications of natural language-based questions that allows for the estimation of development effort by taking into account data sources, interfaces and algorithms.
Authors: Junfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang, Shu Wu, Liang Wang, Tieniu Tan
Abstract: Object hallucination has been an Achilles' heel which hinders the broader applications of large vision-language models (LVLMs). Object hallucination refers to the phenomenon that the LVLMs claim non-existent objects in the image. To mitigate the object hallucinations, instruction tuning and external model-based detection methods have been proposed, which either require large-scare computational resources or depend on the detection result of external models. However, there remains an under-explored field to utilize the LVLM itself to alleviate object hallucinations. In this work, we adopt the intuition that the LVLM tends to respond logically consistently for existent objects but inconsistently for hallucinated objects. Therefore, we propose a Logical Closed Loop-based framework for Object Hallucination Detection and Mitigation, namely LogicCheckGPT. In specific, we devise logical consistency probing to raise questions with logical correlations, inquiring about attributes from objects and vice versa. Whether their responses can form a logical closed loop serves as an indicator of object hallucination. As a plug-and-play method, it can be seamlessly applied to all existing LVLMs. Comprehensive experiments conducted on three benchmarks across four LVLMs have demonstrated significant improvements brought by our method, indicating its effectiveness and generality.
Authors: Matteo Priorelli, Ivilin Peev Stoianov
Abstract: By dynamic planning, we refer to the ability of the human brain to infer and impose motor trajectories related to cognitive decisions. A recent paradigm, active inference, brings fundamental insights into the adaptation of biological organisms, constantly striving to minimize prediction errors to restrict themselves to life-compatible states. Over the past years, many studies have shown how human and animal behavior could be explained in terms of an active inferential process - either as discrete decision-making or continuous motor control - inspiring innovative solutions in robotics and artificial intelligence. Still, the literature lacks a comprehensive outlook on how to effectively plan actions in changing environments. Setting ourselves the goal of modeling tool use, we delve into the topic of dynamic planning in active inference, keeping in mind two crucial aspects of biological goal-directed behavior: the capacity to understand and exploit affordances for object manipulation, and to learn the hierarchical interactions between the self and the environment, including other agents. We start from a simple unit and gradually describe more advanced structures, comparing recently proposed design choices and providing basic examples for each section. This study distances itself from traditional views centered on neural networks and reinforcement learning, and points toward a yet unexplored direction in active inference: hybrid representations in hierarchical models.
Authors: Przemyslaw Biecek, Wojciech Samek
Abstract: Explainable Artificial Intelligence (XAI) is a young but very promising field of research. Unfortunately, the progress in this field is currently slowed down by divergent and incompatible goals. We separate various threads tangled within the area of XAI into two complementary cultures of human/value-oriented explanations (BLUE XAI) and model/validation-oriented explanations (RED XAI). This position paper argues that the area of RED XAI is currently under-explored, i.e., more methods for explainability are desperately needed to question models (e.g., extract knowledge from well-performing models as well as spotting and fixing bugs in faulty models), and the area of RED XAI hides great opportunities and potential for important research necessary to ensure the safety of AI systems. We conclude this paper by presenting promising challenges in this area.
Authors: Xinyi Wang, Qing Zhao, Lang Tong
Abstract: This paper presents a generative artificial intelligence approach to probabilistic forecasting of electricity market signals, such as real-time locational marginal prices and area control error signals. Inspired by the Wiener-Kallianpur innovation representation of nonparametric time series, we propose a weak innovation autoencoder architecture and a novel deep learning algorithm that extracts the canonical independent and identically distributed innovation sequence of the time series, from which samples of future time series are generated. The validity of the proposed approach is established by proving that, under ideal training conditions, the generated samples have the same conditional probability distribution as that of the ground truth. Three applications involving highly dynamic and volatile time series in real-time market operations are considered: (i) locational marginal price forecasting for self-scheduled resources such as battery storage participants, (ii) interregional price spread forecasting for virtual bidders in interchange markets, and (iii) area control error forecasting for frequency regulations. Numerical studies based on market data from multiple independent system operators demonstrate the superior performance of the proposed generative forecaster over leading classical and modern machine learning techniques under both probabilistic and point forecasting metrics.
Authors: Xufeng Cai, Jelena Diakonikolas
Abstract: Incremental gradient and incremental proximal methods are a fundamental class of optimization algorithms used for solving finite sum problems, broadly studied in the literature. Yet, without strong convexity, their convergence guarantees have primarily been established for the ergodic (average) iterate. Motivated by applications in continual learning, we obtain the first convergence guarantees for the last iterate of both incremental gradient and incremental proximal methods, in general convex smooth (for both) and convex Lipschitz (for the proximal variants) settings. Our oracle complexity bounds for the last iterate nearly match (i.e., match up to a square-root-log or a log factor) the best known oracle complexity bounds for the average iterate, for both classes of methods. We further obtain generalizations of our results to weighted averaging of the iterates with increasing weights and for randomly permuted ordering of updates. We study incremental proximal methods as a model of continual learning with generalization and argue that large amount of regularization is crucial to preventing catastrophic forgetting. Our results generalize last iterate guarantees for incremental methods compared to state of the art, as such results were previously known only for overparameterized linear models, which correspond to convex quadratic problems with infinitely many solutions.
Authors: Tobias Schnabel, Jennifer Neville
Abstract: In many modern LLM applications, such as retrieval augmented generation, prompts have become programs themselves. In these settings, prompt programs are repeatedly called with different user queries or data instances. A big practical challenge is optimizing such prompt programs. Recent work has mostly focused on either simple prompt programs or assumed that the general structure of a prompt program is fixed. We introduce SAMMO, a framework to perform symbolic prompt program search for compile-time optimizations of prompt programs. SAMMO represents prompt programs on a symbolic level which allows for a rich set of transformations that can be searched over during optimization. We show that SAMMO generalizes previous methods and improves the performance of complex prompts on (1) instruction tuning, (2) RAG pipeline tuning, and (3) prompt compression, across several different LLMs. We make all code available open-source at https://github.com/microsoft/sammo .
Authors: Maryam Ahang, Mostafa Abbasi, Todd Charter, Homayoun Najjaran
Abstract: Condition monitoring of industrial systems is crucial for ensuring safety and maintenance planning, yet notable challenges arise in real-world settings due to the limited or non-existent availability of fault samples. This paper introduces an innovative solution to this problem by proposing a new method for fault detection and condition monitoring for unseen data. Adopting an approach inspired by zero-shot learning, our method can identify faults and assign a relative health index to various operational conditions. Typically, we have plenty of data on normal operations, some data on compromised conditions, and very few (if any) samples of severe faults. We use a variational autoencoder to capture the probabilistic distribution of previously seen and new unseen conditions. The health status is determined by comparing each sample's deviation from a normal operation reference distribution in the latent space. Faults are detected by establishing a threshold for the health indexes, allowing the model to identify severe, unseen faults with high accuracy, even amidst noise. We validate our approach using the run-to-failure IMS-bearing dataset and compare it with other methods. The health indexes generated by our model closely match the established descriptive model of bearing wear, attesting to the robustness and reliability of our method. These findings highlight the potential of our methodology in augmenting fault detection capabilities within industrial domains, thereby contributing to heightened safety protocols and optimized maintenance practices.
Authors: Tyler Griggs, Xiaoxuan Liu, Jiaxiang Yu, Doyoung Kim, Wei-Lin Chiang, Alvin Cheung, Ion Stoica
Abstract: Large language models (LLMs) are increasingly integrated into many online services, yet they remain cost-prohibitive to deploy due to the requirement of expensive GPU instances. Prior work has addressed the high cost of LLM serving by improving the inference engine, but less attention has been given to selecting the most cost-efficient GPU type(s) for a specific LLM service. There is a large and growing landscape of GPU types and, within these options, higher cost does not always lead to increased performance. Instead, through a comprehensive investigation, we find that three key LLM service characteristics (request size, request rate, SLO) strongly influence GPU cost efficiency, and differing GPU types are most cost efficient for differing LLM service settings. As a result, the most cost-efficient allocation for a given service is typically a mix of heterogeneous GPU types. Based on this analysis, we introduce M\'elange, a GPU allocation framework that navigates these diverse LLM service characteristics and heterogeneous GPU option space to automatically and efficiently derive the minimal-cost GPU allocation for a given LLM service. We formulate the GPU allocation task as a cost-aware bin packing problem where GPUs are bins and items are slices of the service workload. Our formulation's constraints account for a service's unique characteristics, allowing M\'elange to be flexible to support diverse service settings and heterogeneity-aware to adapt the GPU allocation to a specific service. Compared to using only a single GPU type, M\'elange reduces deployment costs by up to 77% in conversational settings, 33% in document-based settings, and 51% in a mixed setting.
Authors: Emile van Krieken, Samy Badreddine, Robin Manhaeve, Eleonora Giunchiglia
Abstract: The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth. There now are a wide variety of NeSy frameworks, each with its own specific language for expressing background knowledge and how to relate it to neural networks. This heterogeneity hinders accessibility for newcomers and makes comparing different NeSy frameworks challenging. We propose a language for NeSy, which we call ULLER, a Unfied Language for LEarning and Reasoning. ULLER encompasses a wide variety of settings, while ensuring that knowledge described in it can be used in existing NeSy systems. ULLER has a first-order logic syntax specialised for NeSy for which we provide example semantics including classical FOL, fuzzy logic, and probabilistic logic. We believe ULLER is a first step towards making NeSy research more accessible and comparable, paving the way for libraries that streamline training and evaluation across a multitude of semantics, knowledge bases, and NeSy systems.
Authors: Fuqiang Cheng, Wei Xie, Hua Zheng
Abstract: Biomanufacturing innovation relies on an efficient Design of Experiments (DoEs) to optimize processes and product quality. Traditional DoE methods, ignoring the underlying bioprocessing mechanisms, often suffer from a lack of interpretability and sample efficiency. This limitation motivates us to create a new optimal learning approach for digital twin model calibration. In this study, we consider the cell culture process multi-scale mechanistic model, also known as Biological System-of-Systems (Bio-SoS). This model with a modular design, composed of sub-models, allows us to integrate data across various production processes. To calibrate the Bio-SoS digital twin, we evaluate the mean squared error of model prediction and develop a computational approach to quantify the impact of parameter estimation error of individual sub-models on the prediction accuracy of digital twin, which can guide sample-efficient and interpretable DoEs.
Authors: Uday Mallappa, Hesham Mostafa, Mikhail Galkin, Mariano Phielipp, Somdeb Majumdar
Abstract: Floorplanning for systems-on-a-chip (SoCs) and its sub-systems is a crucial and non-trivial step of the physical design flow. It represents a difficult combinatorial optimization problem. A typical large scale SoC with 120 partitions generates a search-space of nearly 10E250. As novel machine learning (ML) approaches emerge to tackle such problems, there is a growing need for a modern benchmark that comprises a large training dataset and performance metrics that better reflect real-world constraints and objectives compared to existing benchmarks. To address this need, we present FloorSet -- two comprehensive datasets of synthetic fixed-outline floorplan layouts that reflect the distribution of real SoCs. Each dataset has 1M training samples and 100 test samples where each sample is a synthetic floor-plan. FloorSet-Prime comprises fully-abutted rectilinear partitions and near-optimal wire-length. A simplified dataset that reflects early design phases, FloorSet-Lite comprises rectangular partitions, with under 5 percent white-space and near-optimal wire-length. Both datasets define hard constraints seen in modern design flows such as shape constraints, edge-affinity, grouping constraints, and pre-placement constraints. FloorSet is intended to spur fundamental research on large-scale constrained optimization problems. Crucially, FloorSet alleviates the core issue of reproducibility in modern ML driven solutions to such problems. FloorSet is available as an open-source repository for the research community.
Authors: Jayanth Bhargav, Mahsa Ghasemi, Shreyas Sundaram
Abstract: We consider the problem of selecting an optimal subset of information sources for a hypothesis testing/classification task where the goal is to identify the true state of the world from a finite set of hypotheses, based on finite observation samples from the sources. In order to characterize the learning performance, we propose a misclassification penalty framework, which enables nonuniform treatment of different misclassification errors. In a centralized Bayesian learning setting, we study two variants of the subset selection problem: (i) selecting a minimum cost information set to ensure that the maximum penalty of misclassifying the true hypothesis is below a desired bound and (ii) selecting an optimal information set under a limited budget to minimize the maximum penalty of misclassifying the true hypothesis. Under certain assumptions, we prove that the objective (or constraints) of these combinatorial optimization problems are weak (or approximate) submodular, and establish high-probability performance guarantees for greedy algorithms. Further, we propose an alternate metric for information set selection which is based on the total penalty of misclassification. We prove that this metric is submodular and establish near-optimal guarantees for the greedy algorithms for both the information set selection problems. Finally, we present numerical simulations to validate our theoretical results over several randomly generated instances.
Authors: Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon, David Harel
Abstract: Accelerating the inference of large language models (LLMs) is an important challenge in artificial intelligence. This paper introduces distributed speculative inference (DSI), a novel distributed inference algorithm that is provably faster than speculative inference (SI) [leviathan2023fast, chen2023accelerating, miao2023specinfer] and traditional autoregressive inference (non-SI). Like other SI algorithms, DSI works on frozen LLMs, requiring no training or architectural modifications, and it preserves the target distribution. Prior studies on SI have demonstrated empirical speedups (compared to non-SI) but require a fast and accurate drafter LLM. In practice, off-the-shelf LLMs often do not have matching drafters that are sufficiently fast and accurate. We show a gap: SI gets slower than non-SI when using slower or less accurate drafters. We close this gap by proving that DSI is faster than both SI and non-SI given any drafters. By orchestrating multiple instances of the target and drafters, DSI is not only faster than SI but also supports LLMs that cannot be accelerated with SI. Our simulations show speedups of off-the-shelf LLMs in realistic settings: DSI is 1.29-1.92x faster than SI.
Authors: Daniel Yun
Abstract: In this paper, we introduce a novel method for merging the weights of multiple pre-trained neural networks using a genetic algorithm called MeGA. Traditional techniques, such as weight averaging and ensemble methods, often fail to fully harness the capabilities of pre-trained networks. Our approach leverages a genetic algorithm with tournament selection, crossover, and mutation to optimize weight combinations, creating a more effective fusion. This technique allows the merged model to inherit advantageous features from both parent models, resulting in enhanced accuracy and robustness. Through experiments on the CIFAR-10 dataset, we demonstrate that our genetic algorithm-based weight merging method improves test accuracy compared to individual models and conventional methods. This approach provides a scalable solution for integrating multiple pre-trained networks across various deep learning applications. Github is available at: https://github.com/YUNBLAK/MeGA-Merging-Multiple-Independently-Trained-Neural-Networks-Based-on-Genetic-Algorithm
Authors: Adane Nega Tarekegn
Abstract: The news landscape is continuously evolving, with an ever-increasing volume of information from around the world. Automated event detection within this vast data repository is essential for monitoring, identifying, and categorizing significant news occurrences across diverse platforms. This paper presents an event detection framework that leverages Large Language Models (LLMs) combined with clustering analysis to detect news events from the Global Database of Events, Language, and Tone (GDELT). The framework enhances event clustering through both pre-event detection tasks (keyword extraction and text embedding) and post-event detection tasks (event summarization and topic labelling). We also evaluate the impact of various textual embeddings on the quality of clustering outcomes, ensuring robust news categorization. Additionally, we introduce a novel Cluster Stability Assessment Index (CSAI) to assess the validity and robustness of clustering results. CSAI utilizes multiple feature vectors to provide a new way of measuring clustering quality. Our experiments indicate that the use of LLM embedding in the event detection framework has significantly improved the results, demonstrating greater robustness in terms of CSAI scores. Moreover, post-event detection tasks generate meaningful insights, facilitating effective interpretation of event clustering results. Overall, our experimental results indicate that the proposed framework offers valuable insights and could enhance the accuracy in news analysis and reporting.
Authors: Qianchao Zhu, Jiangfei Duan, Chang Chen, Siran Liu, Xiuhong Li, Guanyu Feng, Xin Lv, Huanqi Cao, Xiao Chuanfu, Xingcheng Zhang, Dahua Lin, Chao Yang
Abstract: Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity require additional pretraining or finetuning, and often sacrifice model accuracy. In this paper, we first provide both theoretical and empirical foundations for near-lossless sparse attention. We find dynamically capturing head-specific sparse patterns at runtime with low overhead is crucial. To address this, we propose SampleAttention, an adaptive structured and near-lossless sparse attention. Leveraging observed significant sparse patterns, SampleAttention attends to a fixed percentage of adjacent tokens to capture local window patterns, and employs a two-stage query-guided key-value filtering approach, which adaptively select a minimum set of key-values with low overhead, to capture column stripe patterns. Comprehensive evaluations show that SampleAttention can seamlessly replace vanilla attention in off-the-shelf LLMs with nearly no accuracy loss, and reduces TTFT by up to $2.42\times$ compared with FlashAttention.
Authors: Rishabh Maheshwary, Vikas Yadav, Hoang Nguyen, Khyati Mahajan, Sathwik Tejaswi Madhusudhan
Abstract: Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they predominantly focus on high-resource languages like English. To better align LLMs across a broad spectrum of languages and tasks, we propose a fully synthetic, novel taxonomy (Evol) guided Multilingual, Multi-turn instruction finetuning dataset, called M2Lingual. It is constructed by first selecting a diverse set of seed examples and then utilizing the proposed Evol taxonomy to convert these seeds into complex and challenging multi-turn instructions. We demonstrate the effectiveness of M2Lingual by training LLMs of varying sizes and showcasing the enhanced performance across a diverse set of languages. We contribute the 2 step Evol taxonomy with the guided generation code: https://github.com/ServiceNow/M2Lingual, as well as the first fully synthetic, general and task-oriented, multi-turn, multilingual dataset built with Evol - M2Lingual: https://huggingface.co/datasets/ServiceNow-AI/ M2Lingual - containing 182K total IFT pairs, covering 70 languages and 17+ NLP tasks.
URLs: https://github.com/ServiceNow/M2Lingual,, https://huggingface.co/datasets/ServiceNow-AI/
Authors: Niful Islam, Khan Md Hasib, Fahmida Akter Joti, Asif Karim, Sami Azam
Abstract: Skin cancer is a major concern to public health, accounting for one-third of the reported cancers. If not detected early, the cancer has the potential for severe consequences. Recognizing the critical need for effective skin cancer classification, we address the limitations of existing models, which are often too large to deploy in areas with limited computational resources. In response, we present a knowledge distillation based approach for creating a lightweight yet high-performing classifier. The proposed solution involves fusing three models, namely ResNet152V2, ConvNeXtBase, and ViT Base, to create an effective teacher model. The teacher model is then employed to guide a lightweight student model of size 2.03 MB. This student model is further compressed to 469.77 KB using 16-bit quantization, enabling smooth incorporation into edge devices. With six-stage image preprocessing, data augmentation, and a rigorous ablation study, the model achieves an impressive accuracy of 98.75% on the HAM10000 dataset and 98.94% on the Kaggle dataset in classifying benign and malignant skin cancers. With its high accuracy and compact size, our model appears to be a potential choice for accurate skin cancer classification, particularly in resource-constrained settings.
Authors: Nawaf Alampara, Santiago Miret, Kevin Maik Jablonka
Abstract: Effectively representing materials as text has the potential to leverage the vast advancements of large language models (LLMs) for discovering new materials. While LLMs have shown remarkable success in various domains, their application to materials science remains underexplored. A fundamental challenge is the lack of understanding of how to best utilize text-based representations for materials modeling. This challenge is further compounded by the absence of a comprehensive benchmark to rigorously evaluate the capabilities and limitations of these text representations in capturing the complexity of material systems. To address this gap, we propose MatText, a suite of benchmarking tools and datasets designed to systematically evaluate the performance of language models in modeling materials. MatText encompasses nine distinct text-based representations for material systems, including several novel representations. Each representation incorporates unique inductive biases that capture relevant information and integrate prior physical knowledge about materials. Additionally, MatText provides essential tools for training and benchmarking the performance of language models in the context of materials science. These tools include standardized dataset splits for each representation, probes for evaluating sensitivity to geometric factors, and tools for seamlessly converting crystal structures into text. Using MatText, we conduct an extensive analysis of the capabilities of language models in modeling materials. Our findings reveal that current language models consistently struggle to capture the geometric information crucial for materials modeling across all representations. Instead, these models tend to leverage local information, which is emphasized in some of our novel representations. Our analysis underscores MatText's ability to reveal shortcomings of text-based methods for materials design.
Authors: Robert Baumgartner, Sicco Verwer
Abstract: Probabilistic deterministic finite automata (PDFA) are discrete event systems modeling conditional probabilities over languages: Given an already seen sequence of tokens they return the probability of tokens of interest to appear next. These types of models have gained interest in the domain of explainable machine learning, where they are used as surrogate models for neural networks trained as language models. In this work we present an algorithm to distill PDFA from neural networks. Our algorithm is a derivative of the L# algorithm and capable of learning PDFA from a new type of query, in which the algorithm infers conditional probabilities from the probability of the queried string to occur. We show its effectiveness on a recent public dataset by distilling PDFA from a set of trained neural networks.
Authors: Mauricio Gomes de Queiroz, Paul Jimenez, Raphael Cardoso, Mateus Vidaletti Costa, Mohab Abdalla, Ian O'Connor, Alberto Bosio, Fabio Pavanello
Abstract: Photonic Neural Networks (PNNs) are gaining significant interest in the research community due to their potential for high parallelization, low latency, and energy efficiency. PNNs compute using light, which leads to several differences in implementation when compared to electronics, such as the need to represent input features in the photonic domain before feeding them into the network. In this encoding process, it is common to combine multiple features into a single input to reduce the number of inputs and associated devices, leading to smaller and more energy-efficient PNNs. Although this alters the network's handling of input data, its impact on PNNs remains understudied. This paper addresses this open question, investigating the effect of commonly used encoding strategies that combine features on the performance and learning capabilities of PNNs. Here, using the concept of feature importance, we develop a mathematical methodology for analyzing feature combination. Through this methodology, we demonstrate that encoding multiple features together in a single input determines their relative importance, thus limiting the network's ability to learn from the data. Given some prior knowledge of the data, however, this can also be leveraged for higher accuracy. By selecting an optimal encoding method, we achieve up to a 12.3% improvement in accuracy of PNNs trained on the Iris dataset compared to other encoding techniques, surpassing the performance of networks where features are not combined. These findings highlight the importance of carefully choosing the encoding to the accuracy and decision-making strategies of PNNs, particularly in size or power constrained applications.
Authors: Xinyu Lian, Sam Ade Jacobs, Lev Kurilenko, Masahiro Tanaka, Stas Bekman, Olatunji Ruwase, Minjia Zhang
Abstract: Existing checkpointing approaches seem ill-suited for distributed training even though hardware limitations make model parallelism, i.e., sharding model state across multiple accelerators, a requirement for model scaling. Consolidating distributed model state into a single checkpoint unacceptably slows down training, and is impractical at extreme scales. Distributed checkpoints, in contrast, are tightly coupled to the model parallelism and hardware configurations of the training run, and thus unusable on different configurations. To address this problem, we propose Universal Checkpointing, a technique that enables efficient checkpoint creation while providing the flexibility of resuming on arbitrary parallelism strategy and hardware configurations. Universal Checkpointing unlocks unprecedented capabilities for large-scale training such as improved resilience to hardware failures through continued training on remaining healthy hardware, and reduced training time through opportunistic exploitation of elastic capacity. The key insight of Universal Checkpointing is the selection of the optimal representation in each phase of the checkpointing life cycle: distributed representation for saving, and consolidated representation for loading. This is achieved using two key mechanisms. First, the universal checkpoint format, which consists of a consolidated representation of each model parameter and metadata for mapping parameter fragments into training ranks of arbitrary model-parallelism configuration. Second, the universal checkpoint language, a simple but powerful specification language for converting distributed checkpoints into the universal checkpoint format. Our evaluation demonstrates the effectiveness and generality of Universal Checkpointing on state-of-the-art model architectures and a wide range of parallelism techniques.
Authors: Shubhankar Singh, Purvi Chaurasia, Yerram Varun, Pranshu Pandya, Vatsal Gupta, Vivek Gupta, Dan Roth
Abstract: Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills. We introduce FlowVQA, a novel benchmark aimed at assessing the capabilities of visual question-answering multimodal language models in reasoning with flowcharts as visual contexts. FlowVQA comprises 2,272 carefully generated and human-verified flowchart images from three distinct content sources, along with 22,413 diverse question-answer pairs, to test a spectrum of reasoning tasks, including information localization, decision-making, and logical progression. We conduct a thorough baseline evaluation on a suite of both open-source and proprietary multimodal language models using various strategies, followed by an analysis of directional bias. The results underscore the benchmark's potential as a vital tool for advancing the field of multimodal modeling, providing a focused and challenging environment for enhancing model performance in visual and logical reasoning tasks.