Authors: Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin, Rahul V. Kulkarni
Abstract: In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized setting has led to improved robustness and exploration for both of these objectives. Recently, the entropy-regularized average-reward problem was addressed using tools from large deviation theory in the tabular setting. This method has the advantage of linearity, providing access to both the optimal policy and average reward-rate through properties of a single matrix. In this paper, we extend that framework to more general settings by developing approaches based on function approximation by neural networks. This formulation reveals new theoretical insights into the relationship between different objectives used in RL. Additionally, we combine our algorithm with a posterior policy iteration scheme, showing how our approach can also solve the average-reward RL problem without entropy-regularization. Using classic control benchmarks, we experimentally find that our method compares favorably with other algorithms in terms of stability and rate of convergence.
Authors: Yikai Hou, Peng Tang
Abstract: Quality-of-service (QoS) data exhibit dynamic temporal patterns that are crucial for accurately predicting missing values. These patterns arise from the evolving interactions between users and services, making it essential to capture the temporal dynamics inherent in such data for improved prediction performance. As the size and complexity of QoS datasets increase, existing models struggle to provide accurate predictions, highlighting the need for more flexible and dynamic methods to better capture the underlying patterns in large-scale QoS data. To address this issue, we introduce a neural network-based tensor factorization approach tailored for learning spatiotemporal representations of high-dimensional and incomplete (HDI) tensors, namely the Multi-head Self-attending Neural Tucker Factorization (MSNTucF). The model is elaborately designed for modeling intricate nonlinear spatiotemporal feature interaction patterns hidden in real world data with a two-fold idea. It first employs a neural network structure to generalize the traditional framework of Tucker factorization and then proposes to leverage a multi-head self-attending module to enforce nonlinear latent interaction learning. In empirical studies on two dynamic QoS datasets from real applications, the proposed MSNTucF model demonstrates superior performance compared to state-of-the-art benchmark models in estimating missing observations. This highlights its ability to learn non-linear spatiotemporal representations of HDI tensors.
Authors: Tong Liu, Hadi Meidani
Abstract: Estimating the shortest travel time and providing route recommendation between different locations in a city or region can quantitatively measure the conditions of the transportation network during or after extreme events. One common approach is to use Dijkstra's Algorithm, which produces the shortest path as well as the shortest distance. However, this option is computationally expensive when applied to large-scale networks. This paper proposes a novel fast framework based on graph neural networks (GNNs) which approximate the single-source shortest distance between pairs of locations, and predict the single-source shortest path subsequently. We conduct multiple experiments on synthetic graphs of different size to demonstrate the feasibility and computational efficiency of the proposed model. In real-world case studies, we also applied the proposed method of flood risk analysis of coastal urban areas to calculate delays in evacuation to public shelters during hurricanes. The results indicate the accuracy and computational efficiency of the GNN model, and its potential for effective implementation in emergency planning and management.
Authors: Maxwell J. Yin, Dingyi Jiang, Yongbing Chen, Boyu Wang, Charles Ling
Abstract: Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly conservative memorization in smaller LLMs, leading to low generalization confidence. As fully preserving the CoT ability of teacher model is impossible, we hypothesize that adversarial CoT fine-tuning is crucial for developing smaller LLM with robust CoT generalization. To this end, we propose \textit{PRompt-Assisted Domain-Adversarial fine-tuning} (PRADA), a principled fine-tuning framework that integrates diverse CoT domains. Specifically, PRADA pioneers two CoT improvements in smaller LLM: (1) Recovering the domain-invariant feature insight which typically lost during distillation with domain adversarial fine-tuning; (2) Enhancing the domain adaptability of CoT prompt engineering by employing domain-adversarial approaches. We theoretically demonstrate the effectiveness of our approach and empirically show that it significantly outperforms the state of the arts in a wide range of tasks. Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.
Authors: Daniele Castellana, Filippo Maria Bianchi
Abstract: We introduce BN-Pool, the first clustering-based pooling method for Graph Neural Networks (GNNs) that adaptively determines the number of supernodes in a coarsened graph. By leveraging a Bayesian non-parametric framework, BN-Pool employs a generative model capable of partitioning graph nodes into an unbounded number of clusters. During training, we learn the node-to-cluster assignments by combining the supervised loss of the downstream task with an unsupervised auxiliary term, which encourages the reconstruction of the original graph topology while penalizing unnecessary proliferation of clusters. This adaptive strategy allows BN-Pool to automatically discover an optimal coarsening level, offering enhanced flexibility and removing the need to specify sensitive pooling ratios. We show that BN-Pool achieves superior performance across diverse benchmarks.
Authors: Zhou Ni, Masoud Ghazikor, Morteza Hashemi
Abstract: Traditional Federated Learning (FL) approaches often struggle with data heterogeneity across clients, leading to suboptimal model performance for individual clients. To address this issue, Personalized Federated Learning (PFL) emerges as a solution to the challenges posed by non-independent and identically distributed (non-IID) and unbalanced data across clients. Furthermore, in most existing decentralized machine learning works, a perfect communication channel is considered for model parameter transmission between clients and servers. However, decentralized PFL over wireless links introduces new challenges, such as resource allocation and interference management. To overcome these challenges, we formulate a joint optimization problem that incorporates the underlying device-to-device (D2D) wireless channel conditions into a server-free PFL approach. The proposed method, dubbed pFedWN, optimizes the learning performance for each client while accounting for the variability in D2D wireless channels. To tackle the formulated problem, we divide it into two sub-problems: PFL neighbor selection and PFL weight assignment. The PFL neighbor selection is addressed through channel-aware neighbor selection within unlicensed spectrum bands such as ISM bands. Next, to assign PFL weights, we utilize the Expectation-Maximization (EM) method to evaluate the similarity between clients' data and obtain optimal weight distribution among the chosen PFL neighbors. Empirical results show that pFedWN provides efficient and personalized learning performance with non-IID and unbalanced datasets. Furthermore, it outperforms the existing FL and PFL methods in terms of learning efficacy and robustness, particularly under dynamic and unpredictable wireless channel conditions.
Authors: En-hui Yang, Shayan Mohajer Hamidi
Abstract: The success of deep learning (DL) is often achieved with large models and high complexity during both training and post-training inferences, hindering training in resource-limited settings. To alleviate these issues, this paper introduces a new framework dubbed ``coded deep learning'' (CDL), which integrates information-theoretic coding concepts into the inner workings of DL, to significantly compress model weights and activations, reduce computational complexity at both training and post-training inference stages, and enable efficient model/data parallelism. Specifically, within CDL, (i) we first propose a novel probabilistic method for quantizing both model weights and activations, and its soft differentiable variant which offers an analytic formula for gradient calculation during training; (ii) both the forward and backward passes during training are executed over quantized weights and activations, eliminating most floating-point operations and reducing training complexity; (iii) during training, both weights and activations are entropy constrained so that they are compressible in an information-theoretic sense throughout training, thus reducing communication costs in model/data parallelism; and (iv) the trained model in CDL is by default in a quantized format with compressible quantized weights, reducing post-training inference and storage complexity. Additionally, a variant of CDL, namely relaxed CDL (R-CDL), is presented to further improve the trade-off between validation accuracy and compression though requiring full precision in training with other advantageous features of CDL intact. Extensive empirical results show that CDL and R-CDL outperform the state-of-the-art algorithms in DNN compression in the literature.
Authors: Gautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos, Kevin Tian
Abstract: We study the problem of PAC learning $\gamma$-margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the Perspectron, that has sample complexity $\widetilde{O}((\epsilon\gamma)^{-2})$ and achieves classification error at most $\eta+\epsilon$ where $\eta$ is the Massart noise rate. Prior works [DGT19,CKMY20] came with worse sample complexity guarantees (in both $\epsilon$ and $\gamma$) or could only handle random classification noise [DDK+23,KIT+23] -- a much milder noise assumption. We also show that our results extend to the more challenging setting of learning generalized linear models with a known link function under Massart noise, achieving a similar sample complexity to the halfspace case. This significantly improves upon the prior state-of-the-art in this setting due to [CKMY20], who introduced this model.
Authors: Peilang Li, Umer Siddique, Yongcan Cao
Abstract: Deep reinforcement learning (RL) has shown remarkable success in complex domains, however, the inherent black box nature of deep neural network policies raises significant challenges in understanding and trusting the decision-making processes. While existing explainable RL methods provide local insights, they fail to deliver a global understanding of the model, particularly in high-stakes applications. To overcome this limitation, we propose a novel model-agnostic approach that bridges the gap between explainability and interpretability by leveraging Shapley values to transform complex deep RL policies into transparent representations. The proposed approach offers two key contributions: a novel approach employing Shapley values to policy interpretation beyond local explanations and a general framework applicable to off-policy and on-policy algorithms. We evaluate our approach with three existing deep RL algorithms and validate its performance in two classic control environments. The results demonstrate that our approach not only preserves the original models' performance but also generates more stable interpretable policies.
Authors: Michael Guevarra (Illumia Labs), Indronil Bhattacharjee (New Mexico State University), Srijita Das (University of Michigan-Dearborn), Christabel Wayllace (New Mexico State University), Carrie Demmans Epp (University of Alberta), Matthew E. Taylor (University of Alberta, Alberta Machine Intelligence Institute), Alan Tay (Illumia Labs)
Abstract: Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication -- one-to-one interaction in real-world scenarios is preferred to lecture-style information delivery. This paper introduces a framework that allows instructors to collaborate with large language models to dynamically design realistic scenarios for students to communicate. Our framework uses these scenarios to enable student rehearsal, provide immediate feedback, and visualize performance for both students and instructors. Unlike traditional intelligent tutoring systems, instructors can easily co-create scenarios with a large language model without technical skills. Additionally, the system generates new scenario branches in real time when existing options do not fit the student's response.
Authors: Yahya Badran, Christine Preisach
Abstract: Knowledge tracing (KT) models aim to predict students' future performance based on their historical interactions. Most existing KT models rely exclusively on human-defined knowledge concepts (KCs) associated with exercises. As a result, the effectiveness of these models is highly dependent on the quality and completeness of the predefined KCs. Human errors in labeling and the cost of covering all potential underlying KCs can limit model performance. In this paper, we propose a KT model, Sparse Binary Representation KT (SBRKT), that generates new KC labels, referred to as auxiliary KCs, which can augment the predefined KCs to address the limitations of relying solely on human-defined KCs. These are learned through a binary vector representation, where each bit indicates the presence (one) or absence (zero) of an auxiliary KC. The resulting discrete representation allows these auxiliary KCs to be utilized in training any KT model that incorporates KCs. Unlike pre-trained dense embeddings, which are limited to models designed to accept such vectors, our discrete representations are compatible with both classical models, such as Bayesian Knowledge Tracing (BKT), and modern deep learning approaches. To generate this discrete representation, SBRKT employs a binarization method that learns a sparse representation, fully trainable via stochastic gradient descent. Additionally, SBRKT incorporates a recurrent neural network (RNN) to capture temporal dynamics and predict future student responses by effectively combining the auxiliary and predefined KCs. Experimental results demonstrate that SBRKT outperforms the tested baselines on several datasets and achieves competitive performance on others. Furthermore, incorporating the learned auxiliary KCs consistently enhances the performance of BKT across all tested datasets.
Authors: Tao Shan, Xin Zhang, Di Wu
Abstract: In this paper, we present a graph neural networks (GNNs)-based fast solver (GraphSolver) for solving combined field integral equations (CFIEs) of 3D conducting bodies. Rao-Wilton-Glisson (RWG) basis functions are employed to discretely and accurately represent the geometry of 3D conducting bodies. A concise and informative graph representation is then constructed by treating each RWG function as a node in the graph, enabling the flow of current between nodes. With the transformed graphs, GraphSolver is developed to directly predict real and imaginary parts of the x, y and z components of the surface current densities at each node (RWG function). Numerical results demonstrate the efficacy of GraphSolver in solving CFIEs for 3D conducting bodies with varying levels of geometric complexity, including basic 3D targets, missile-shaped targets, and airplane-shaped targets.
Authors: Samuel Soo, Wesley Teng, Chandrasekaran Balaganesh
Abstract: Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques often lack precision and interpretability in how they influence model outputs. We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method that leverages insights from Contrastive Activation Addition (CAA) and Sparse Autoencoder-Targeted Steering (SAE-TS). By operating in the latent space of a Sparse Autoencoder (SAE) and employing optimization techniques to select desired SAE features, FGAA constructs precise steering vectors that provide better steering effects while maintaining coherence of steered model outputs. In this regard, evaluations on Gemma-2-2B and Gemma-2-9B models across various steering tasks demonstrate that FGAA outperforms existing steering methods of CAA, SAE decoder steering, and SAE-TS. Our results also highlight important trade-offs between steering scale and general model capabilities that are consistent across all tested steering methods.
Authors: Xiaohong Yang, Minghui Liwang, Xianbin Wang, Zhipeng Cheng, Seyyedali Hosseinalipour, Huaiyu Dai, Zhenzhen Jiao
Abstract: The rapid growth of AI-enabled Internet of Vehicles (IoV) calls for efficient machine learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence of Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in the literature on VEC-HFL is that vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial challenges. First, improper aggregation rules can lead to model obsolescence and prolonged training times. Second, vehicular mobility may result in inefficient data utilization by preventing the vehicles from returning their models to the network edge. Third, achieving a balanced resource allocation across diverse tasks becomes of paramount importance as it majorly affects the effectiveness of collaborative training. We take one of the first steps towards addressing these challenges via proposing a framework for multi-model training in dynamic VEC-HFL with the goal of minimizing global training latency while ensuring balanced training across various tasks-a problem that turns out to be NP-hard. To facilitate timely model training, we introduce a hybrid synchronous-asynchronous aggregation rule. Building on this, we present a novel method called Hybrid Evolutionary And gReedy allocaTion (HEART). The framework operates in two stages: first, it achieves balanced task scheduling through a hybrid heuristic approach that combines improved Particle Swarm Optimization (PSO) and Genetic Algorithms (GA); second, it employs a low-complexity greedy algorithm to determine the training priority of assigned tasks on vehicles. Experiments on real-world datasets demonstrate the superiority of HEART over existing methods.
Authors: Jianhui Sun, Xidong Wu, Heng Huang, Aidong Zhang
Abstract: Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private. With an increasing scale of clients and models, FL encounters two key challenges, client drift due to a high degree of statistical/system heterogeneity, and lack of adaptivity. However, most existing FL research is based on unrealistic assumptions that virtually ignore system heterogeneity. In this paper, we propose Client-Centric Federated Adaptive Optimization, which is a class of novel federated adaptive optimization approaches. We enable several features in this framework such as arbitrary client participation, asynchronous server aggregation, and heterogeneous local computing, which are ubiquitous in real-world FL systems but are missed in most existing works. We provide a rigorous convergence analysis of our proposed framework for general nonconvex objectives, which is shown to converge with the best-known rate. Extensive experiments show that our approaches consistently outperform the baseline by a large margin across benchmarks.
Authors: J. Pablo Mu\~noz, Jinjie Yuan, Nilesh Jain
Abstract: Recently, state-of-the-art approaches for pruning large pre-trained models (LPMs) have demonstrated that the training-free removal of non-critical residual blocks in Transformers is viable for reducing model size, achieving results that outperform previous training-free pruning approaches. Motivated by these findings, we extend BlockPruner (Zhong et al., 2024) and propose MultiPruner, a pruning approach that surpasses recent training-free pruning methods by adopting a multidimensional, iterative, fine-grained pruning strategy. In MultiPruner, multidimensional pruning reinstates the structural balance in block-pruned models by sequentially compressing along three dimensions: i) residual blocks, ii) channels of multilayer perceptrons (MLP), and iii) attention heads. This solution enhances zero-shot accuracy on downstream tasks compared to other techniques while improving model compression ratios, producing compressed models with fewer computing and memory requirements. Extensive experiments demonstrate the advantages of the proposed method across various large pre-trained models. The code and pruning configurations are available at https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.
URLs: https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.
Authors: Jamin Seo, Akshat Ramachandran, Yu-Chuan Chuang, Anirudh Itagi, Tushar Krishna
Abstract: Design space exploration (DSE) plays a crucial role in enabling custom hardware architectures, particularly for emerging applications like AI, where optimized and specialized designs are essential. With the growing complexity of deep neural networks (DNNs) and the introduction of advanced foundational models (FMs), the design space for DNN accelerators is expanding at an exponential rate. Additionally, this space is highly non-uniform and non-convex, making it increasingly difficult to navigate and optimize. Traditional DSE techniques rely on search-based methods, which involve iterative sampling of the design space to find the optimal solution. However, this process is both time-consuming and often fails to converge to the global optima for such design spaces. Recently, AIrchitect v1, the first attempt to address the limitations of search-based techniques, transformed DSE into a constant-time classification problem using recommendation networks. In this work, we propose AIrchitect v2, a more accurate and generalizable learning-based DSE technique applicable to large-scale design spaces that overcomes the shortcomings of earlier approaches. Specifically, we devise an encoder-decoder transformer model that (a) encodes the complex design space into a uniform intermediate representation using contrastive learning and (b) leverages a novel unified representation blending the advantages of classification and regression to effectively explore the large DSE space without sacrificing accuracy. Experimental results evaluated on 10^5 real DNN workloads demonstrate that, on average, AIrchitect v2 outperforms existing techniques by 15% in identifying optimal design points. Furthermore, to demonstrate the generalizability of our method, we evaluate performance on unseen model workloads (LLMs) and attain a 1.7x improvement in inference latency on the identified hardware architecture.
Authors: Fuseini Mumuni, Alhassan Mumuni
Abstract: Artificial Intelligence (AI) has continued to achieve tremendous success in recent times. However, the decision logic of these frameworks is often not transparent, making it difficult for stakeholders to understand, interpret or explain their behavior. This limitation hinders trust in machine learning systems and causes a general reluctance towards their adoption in practical applications, particularly in mission-critical domains like healthcare and autonomous driving. Explainable AI (XAI) techniques facilitate the explainability or interpretability of machine learning models, enabling users to discern the basis of the decision and possibly avert undesirable behavior. This comprehensive survey details the advancements of explainable AI methods, from inherently interpretable models to modern approaches for achieving interpretability of various black box models, including large language models (LLMs). Additionally, we review explainable AI techniques that leverage LLM and vision-language model (VLM) frameworks to automate or improve the explainability of other machine learning models. The use of LLM and VLM as interpretability methods particularly enables high-level, semantically meaningful explanations of model decisions and behavior. Throughout the paper, we highlight the scientific principles, strengths and weaknesses of state-of-the-art methods and outline different areas of improvement. Where appropriate, we also present qualitative and quantitative comparison results of various methods to show how they compare. Finally, we discuss the key challenges of XAI and directions for future research.
Authors: Xu Chu, Hanlin Xue, Bingce Wang, Xiaoyang Liu, Weiping Li, Tong Mo, Tuoyu Feng, Zhijie Tan
Abstract: Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in edges caused by random noise, overemphasizing recent edges while neglecting earlier ones may lead to the model capturing noise. To address this issue, we propose STAA (SpatioTemporal Activity-Aware Random Walk Diffusion). STAA identifies nodes likely to have noisy edges in spatiotemporal dimensions. Spatially, it analyzes critical topological positions through graph wavelet coefficients. Temporally, it analyzes edge evolution through graph wavelet coefficient change rates. Then, random walks are used to reduce the weights of noisy edges, deriving a diffusion matrix containing spatiotemporal information as an augmented adjacency matrix for dynamic GNN learning. Experiments on multiple datasets show that STAA outperforms other dynamic graph augmentation methods in node classification and link prediction tasks.
Authors: Xiaoyang Cao, Dingyi Zhuang, Jinhua Zhao, Shenhao Wang
Abstract: Effective traffic prediction is a cornerstone of intelligent transportation systems, enabling precise forecasts of traffic flow, speed, and congestion. While traditional spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in short-term traffic forecasting, their performance in long-term predictions remains limited. This challenge arises from over-squashing problem, where bottlenecks and limited receptive fields restrict information flow and hinder the modeling of global dependencies. To address these challenges, this study introduces a novel framework that incorporates virtual nodes, which are additional nodes added to the graph and connected to existing nodes, in order to aggregate information across the entire graph within a single GNN layer. Our proposed model incorporates virtual nodes by constructing a semi-adaptive adjacency matrix. This matrix integrates distance-based and adaptive adjacency matrices, allowing the model to leverage geographical information while also learning task-specific features from data. Experimental results demonstrate that the inclusion of virtual nodes significantly enhances long-term prediction accuracy while also improving layer-wise sensitivity to mitigate the over-squashing problem. Virtual nodes also offer enhanced explainability by focusing on key intersections and high-traffic areas, as shown by the visualization of their adjacency matrix weights on road network heat maps. Our advanced approach enhances the understanding and management of urban traffic systems, making it particularly well-suited for real-world applications.
Authors: Maxime De Bois, Flora Parmentier, Rapha\"el Puget, Matthew Tanti, Jordan Peltier
Abstract: To take the esports scene to the next level, we introduce PandaSkill, a framework for assessing player performance and skill rating. Traditional rating systems like Elo and TrueSkill often overlook individual contributions and face challenges in professional esports due to limited game data and fragmented competitive scenes. PandaSkill leverages machine learning to estimate in-game player performance from individual player statistics. Each in-game role is modeled independently, ensuring a fair comparison between them. Then, using these performance scores, PandaSkill updates the player skill ratings using the Bayesian framework OpenSkill in a free-for-all setting. In this setting, skill ratings are updated solely based on performance scores rather than game outcomes, hightlighting individual contributions. To address the challenge of isolated rating pools that hinder cross-regional comparisons, PandaSkill introduces a dual-rating system that combines players' regional ratings with a meta-rating representing each region's overall skill level. Applying PandaSkill to five years of professional League of Legends matches worldwide, we show that our method produces skill ratings that better predict game outcomes and align more closely with expert opinions compared to existing methods.
Authors: Gansen Hu, Zhaoguo Wang, Jinglin Wei, Wei Huang, Haibo Chen
Abstract: Large language models (LLMs) demonstrate remarkable capabilities but face deployment challenges due to their massive parameter counts. While existing compression techniques like pruning can reduce model size, it leads to significant accuracy degradation under high compression ratios. We present a novel perspective inspired by constant folding in compiler optimization. Our approach enables parameter reduction by treating activation functions in LLMs as linear functions. However, recent LLMs use complex non-linear activations like GELU that prevent direct application of this technique. We propose TARDIS, which enables optimization of LLMs with non-linear activations by partially approximating them with linear functions in frequently occurring input ranges. For outlier inputs, TARDIS employs an online predictor to dynamically fall back to original computations. Our experiments demonstrate that TARDIS achieves 80% parameter reduction in feed-forward networks, while significantly outperforming state-of-the-art pruning methods Wanda and RIA with up to 65% higher accuracy. In practical deployments for a 7B model, TARDIS achieves 1.6x end-to-end inference speedup when integrated with the vLLM serving system, and 1.4x speedup with the widely adopted HuggingFace implementation, while incurring only a 10.9% accuracy trade-off.
Authors: Jinyuan Feng, Zhiqiang Pu, Tianyi Hu, Dongmin Li, Xiaolin Ai, Huimu Wang
Abstract: Building mixture-of-experts (MoE) architecture for Low-rank adaptation (LoRA) is emerging as a potential direction in parameter-efficient fine-tuning (PEFT) for its modular design and remarkable performance. However, simply stacking the number of experts cannot guarantee significant improvement. In this work, we first conduct qualitative analysis to indicate that experts collapse to similar representations in vanilla MoE, limiting the capacity of modular design and computational efficiency. Ulteriorly, Our analysis reveals that the performance of previous MoE variants maybe limited by a lack of diversity among experts. Motivated by these findings, we propose Orthogonal Mixture-of-Experts (OMoE), a resource-efficient MoE variant that trains experts in an orthogonal manner to promote diversity. In OMoE, a Gram-Schmidt process is leveraged to enforce that the experts' representations lie within the Stiefel manifold. By applying orthogonal constraints directly to the architecture, OMoE keeps the learning objective unchanged, without compromising optimality. Our method is simple and alleviates memory bottlenecks, as it incurs minimal experts compared to vanilla MoE models. Experiments on diverse commonsense reasoning benchmarks demonstrate that OMoE can consistently achieve stable and efficient performance improvement when compared with the state-of-the-art methods while significantly reducing the number of required experts.
Authors: Roshni Agrawal, Sivakumar Subramanian, Venkataramana Runkana
Abstract: Solar irradiance clustering can enhance solar power capacity planning and help improve forecasting models by identifying similar irradiance patterns influenced by seasonal and weather changes. In this study, we adopt an efficient two-level clustering approach to automatically identify seasons using the clear sky irradiance in first level and subsequently to identify daily cloud level as clear, cloudy and partly cloudy within each season in second level. In the second level of clustering, three methods are compared, namely, Daily Irradiance Index (DII or $\beta$), Euclidean Distance (ED), and Dynamic Time Warping (DTW) distance. The DII is computed as the ratio of time integral of measured irradiance to time integral of the clear sky irradiance. The identified clusters were compared quantitatively using established clustering metrics and qualitatively by comparing the mean irradiance profiles. The results clearly establish the superiority of the $\beta$-based clustering approach as the leader, setting a new benchmark for solar irradiance clustering studies. Moreover, $\beta$-based clustering remains effective even for annual data unlike the time-series methods which suffer significant performance degradation. Interestingly, contrary to expectations, ED-based clustering outperforms the more compute-intensive DTW distance-based clustering. The method has been rigorously validated using data from two distinct US locations, demonstrating robust scalability for larger datasets and potential applicability for other locations.
Authors: Toiba Noor, Soban Nasir Lone, G. V. Ramana, Rajdip Nayek
Abstract: In geotechnical engineering, constitutive models play a crucial role in describing soil behavior under varying loading conditions. Data-driven deep learning (DL) models offer a promising alternative for developing predictive constitutive models. When prediction is the primary focus, quantifying the predictive uncertainty of a trained DL model and communicating this uncertainty to end users is crucial for informed decision-making. This study proposes a recursive Bayesian neural network (rBNN) framework, which builds upon recursive feedforward neural networks (rFFNNs) by introducing generalized Bayesian inference for uncertainty quantification. A significant contribution of this work is the incorporation of a sliding window approach in rFFNNs, allowing the models to effectively capture temporal dependencies across load steps. The rBNN extends this framework by treating model parameters as random variables, with their posterior distributions inferred using generalized variational inference. The proposed framework is validated on two datasets: (i) a numerically simulated consolidated drained (CD) triaxial dataset employing a hardening soil model and (ii) an experimental dataset comprising 28 CD triaxial tests on Baskarp sand. Comparative analyses with LSTM, Bi-LSTM, and GRU models demonstrate that the deterministic rFFNN achieves superior predictive accuracy, attributed to its transparent structure and sliding window design. While the rBNN marginally trails in accuracy for the experimental case, it provides robust confidence intervals, addressing data sparsity and measurement noise in experimental conditions. The study underscores the trade-offs between deterministic and probabilistic approaches and the potential of rBNNs for uncertainty-aware constitutive modeling.
Authors: Gongxu Luo, Haoyue Dai, Boyang Sun, Loka Li, Biwei Huang, Petar Stojanov, Kun Zhang
Abstract: Gene Regulatory Network Inference (GRNI) aims to identify causal relationships among genes using gene expression data, providing insights into regulatory mechanisms. A significant yet often overlooked challenge is selection bias, a process where only cells meeting specific criteria, such as gene expression thresholds, survive or are observed, distorting the true joint distribution of genes and thus biasing GRNI results. Furthermore, gene expression is influenced by latent confounders, such as non-coding RNAs, which add complexity to GRNI. To address these challenges, we propose GISL (Gene Regulatory Network Inference in the presence of Selection bias and Latent confounders), a novel algorithm to infer true regulatory relationships in the presence of selection and confounding issues. Leveraging data obtained via multiple gene perturbation experiments, we show that the true regulatory relationships, as well as selection processes and latent confounders can be partially identified without strong parametric models and under mild graphical assumptions. Experimental results on both synthetic and real-world single-cell gene expression datasets demonstrate the superiority of GISL over existing methods.
Authors: Jivat Neet Kaur, Michael I. Jordan, Ahmed Alaa
Abstract: Standard conformal prediction offers a marginal guarantee on coverage, but for prediction sets to be truly useful, they should ideally ensure coverage conditional on each test point. Unfortunately, it is impossible to achieve exact, distribution-free conditional coverage in finite samples. In this work, we propose an alternative conformal prediction algorithm that targets coverage where it matters most--in instances where a classifier is overconfident in its incorrect predictions. We start by dissecting miscoverage events in marginally-valid conformal prediction, and show that miscoverage rates vary based on the classifier's confidence and its deviation from the Bayes optimal classifier. Motivated by this insight, we develop a variant of conformal prediction that targets coverage conditional on a reduced set of two variables: the classifier's confidence in a prediction and a nonparametric trust score that measures its deviation from the Bayes classifier. Empirical evaluation on multiple image datasets shows that our method generally improves conditional coverage properties compared to standard conformal prediction, including class-conditional coverage, coverage over arbitrary subgroups, and coverage over demographic groups.
Authors: Joseanne Viana, Boris Galkin, Lester Ho, Holger Claussen
Abstract: Unmanned Aerial Vehicles (UAVs) are increasingly essential in various fields such as surveillance, reconnaissance, and telecommunications. This study aims to develop a learning algorithm for the path planning of UAV wireless communication relays, which can reduce storage requirements and accelerate Deep Reinforcement Learning (DRL) convergence. Assuming the system possesses terrain maps of the area and can estimate user locations using localization algorithms or direct GPS reporting, it can input these parameters into the learning algorithms to achieve optimized path planning performance. However, higher resolution terrain maps are necessary to extract topological information such as terrain height, object distances, and signal blockages. This requirement increases memory and storage demands on UAVs while also lengthening convergence times in DRL algorithms. Similarly, defining the telecommunication coverage map in UAV wireless communication relays using these terrain maps and user position estimations demands higher memory and storage utilization for the learning path planning algorithms. Our approach reduces path planning training time by applying a dimensionality reduction technique based on Principal Component Analysis (PCA), sample combination, Prioritized Experience Replay (PER), and the combination of Mean Squared Error (MSE) and Mean Absolute Error (MAE) loss calculations in the coverage map estimates, thereby enhancing a Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The proposed solution reduces the convergence episodes needed for basic training by approximately four times compared to the traditional TD3.
Authors: Georgios Antonopoulos, Shammi More, Simon B. Eickhoff, Federico Raimondo, Kaustubh R. Patil
Abstract: Predictive modeling using structural magnetic resonance imaging (MRI) data is a prominent approach to study brain-aging. Machine learning algorithms and feature extraction methods have been employed to improve predictions and explore healthy and accelerated aging e.g. neurodegenerative and psychiatric disorders. The high-dimensional MRI data pose challenges to building generalizable and interpretable models as well as for data privacy. Common practices are resampling or averaging voxels within predefined parcels, which reduces anatomical specificity and biological interpretability as voxels within a region may differently relate to aging. Effectively, naive fusion by averaging can result in information loss and reduced accuracy. We present a conceptually novel two-level stacking ensemble (SE) approach. The first level comprises regional models for predicting individuals' age based on voxel-wise information, fused by a second-level model yielding final predictions. Eight data fusion scenarios were explored using as input Gray matter volume (GMV) estimates from four datasets covering the adult lifespan. Performance, measured using mean absolute error (MAE), R2, correlation and prediction bias, showed that SE outperformed the region-wise averages. The best performance was obtained when first-level regional predictions were obtained as out-of-sample predictions on the application site with second-level models trained on independent and site-specific data (MAE=4.75 vs baseline regional mean GMV MAE=5.68). Performance improved as more datasets were used for training. First-level predictions showed improved and more robust aging signal providing new biological insights and enhanced data privacy. Overall, the SE improves accuracy compared to the baseline while preserving or enhancing data privacy.
Authors: Valentio Iverson, Stephen Vavasis
Abstract: Parameter estimation is a fundamental challenge in machine learning, crucial for tasks such as neural network weight fitting and Bayesian inference. This paper focuses on the complexity of estimating translation $\boldsymbol{\mu} \in \mathbb{R}^l$ and shrinkage $\sigma \in \mathbb{R}_{++}$ parameters for a distribution of the form $\frac{1}{\sigma^l} f_0 \left( \frac{\boldsymbol{x} - \boldsymbol{\mu}}{\sigma} \right)$, where $f_0$ is a known density in $\mathbb{R}^l$ given $n$ samples. We highlight that while the problem is NP-hard for Maximum Likelihood Estimation (MLE), it is possible to obtain $\varepsilon$-approximations for arbitrary $\varepsilon > 0$ within $\text{poly} \left( \frac{1}{\varepsilon} \right)$ time using the Wasserstein distance.
Authors: Muhammad Bilal, Luis Carretero Lopez
Abstract: Spatiotemporal forecasting is critical in applications such as traffic prediction, climate modeling, and environmental monitoring. However, the prevalence of missing data in real-world sensor networks significantly complicates this task. In this paper, we introduce the Temporal Graph MLP-Mixer (T-GMM), a novel architecture designed to address these challenges. The model combines node-level processing with patch-level subgraph encoding to capture localized spatial dependencies while leveraging a three-dimensional MLP-Mixer to handle temporal, spatial, and feature-based dependencies. Experiments on the AQI, ENGRAD, PV-US and METR-LA datasets demonstrate the model's ability to effectively forecast even in the presence of significant missing data. While not surpassing state-of-the-art models in all scenarios, the T-GMM exhibits strong learning capabilities, particularly in capturing long-range dependencies. These results highlight its potential for robust, scalable spatiotemporal forecasting.
Authors: Matthew Baron, Alex Karpinski
Abstract: A systematic comparison of Chronos, a transformer-based time series forecasting framework, against traditional approaches including ARIMA and Prophet. We evaluate these models across multiple time horizons and user categories, with a focus on the impact of historical context length. Our analysis reveals that while Chronos demonstrates superior performance for longer-term predictions and maintains accuracy with increased context, traditional models show significant degradation as context length increases. We find that prediction quality varies systematically between user classes, suggesting that underlying behavior patterns always influence model performance. This study provides a case for deploying Chronos in real-world applications where limited model tuning is feasible, especially in scenarios requiring longer prediction.
Authors: Fred Shone, Tim Hillel
Abstract: We model human activity scheduling behaviour using a deep generative machine learning approach. Activity schedules, which represent the activities and associated travel behaviours of individuals, are a core component of many applied models in the transport, energy and epidemiology domains. Our data driven approach learns human preferences and scheduling logic without the need for complex interacting combinations of sub-models and custom-rules, this makes our approach significantly faster and simpler to operate that existing approaches. We find activity schedule data combines aspects of both continuous image data and also discrete text data, requiring novel approaches. We additionally contribute a novel schedule representation and comprehensive evaluation framework for generated schedules. Evaluation shows our approach is able to rapidly generate large, diverse and realistic synthetic samples of activity schedules.
Authors: Georgios Vardakas, Antonia Karra, Evaggelia Pitoura, Aristidis Likas
Abstract: Counterfactuals have been recognized as an effective approach to explain classifier decisions. Nevertheless, they have not yet been considered in the context of clustering. In this work, we propose the use of counterfactuals to explain clustering solutions. First, we present a general definition for counterfactuals for model-based clustering that includes plausibility and feasibility constraints. Then we consider the counterfactual generation problem for k-means and Gaussian clustering assuming Euclidean distance. Our approach takes as input the factual, the target cluster, a binary mask indicating actionable or immutable features and a plausibility factor specifying how far from the cluster boundary the counterfactual should be placed. In the k-means clustering case, analytical mathematical formulas are presented for computing the optimal solution, while in the Gaussian clustering case (assuming full, diagonal, or spherical covariances) our method requires the numerical solution of a nonlinear equation with a single parameter only. We demonstrate the advantages of our approach through illustrative examples and quantitative experimental comparisons.
Authors: Sarah Mameche, L\'ena\"ig Cornanguer, Urmi Ninad, Jilles Vreeken
Abstract: Understanding causality is challenging and often complicated by changing causal relationships over time and across environments. Climate patterns, for example, shift over time with recurring seasonal trends, while also depending on geographical characteristics such as ecosystem variability. Existing methods for discovering causal graphs from time series either assume stationarity, do not permit both temporal and spatial distribution changes, or are unaware of locations with the same causal relationships. In this work, we therefore unify the three tasks of causal graph discovery in the non-stationary multi-context setting, of reconstructing temporal regimes, and of partitioning datasets and time intervals into those where invariant causal relationships hold. To construct a consistent score that forms the basis of our method, we employ the Minimum Description Length principle. Our resulting algorithm SPACETIME simultaneously accounts for heterogeneity across space and non-stationarity over time. Given multiple time series, it discovers regime changepoints and a temporal causal graph using non-parametric functional modeling and kernelized discrepancy testing. We also show that our method provides insights into real-world phenomena such as river-runoff measured at different catchments and biosphere-atmosphere interactions across ecosystems.
Authors: Elena Albu, Shan Gao, Pieter Stijnen, Frank E. Rademakers, Bas C T van Bussel, Taya Collyer, Tina Hernandez-Boussard, Laure Wynants, Ben Van Calster
Abstract: Dynamic predictive modeling using electronic health record (EHR) data has gained significant attention in recent years. The reliability and trustworthiness of such models depend heavily on the quality of the underlying data, which is largely determined by the stages preceding the model development: data extraction from EHR systems and data preparation. We list over forty challenges encountered during these stages and provide actionable recommendations for addressing them. These challenges are organized into four categories: cohort definition, outcome definition, feature engineering, and data cleaning. This list is designed to serve as a practical guide for data extraction engineers and researchers, supporting better practices and improving the quality and real-world applicability of dynamic prediction models in clinical settings.
Authors: Busra Tegin, Muhammad Atif Ali, Tolga M Duman
Abstract: Deep neural networks provide reliable solutions for many classification and regression tasks; however, their application in real-time wireless systems with simple sensor networks is limited due to high energy consumption and significant bandwidth needs. This study proposes a multi-sensor wireless inference system with memristor-based analog computing. Given the sensors' limited computational capabilities, the features from the network's front end are transmitted to a central device where an $L_p$-norm inspired approximation of the maximum operation is employed to achieve transformation-invariant features, enabling efficient over-the-air transmission. We also introduce a trainable over-the-air sensor fusion method based on $L_p$-norm inspired combining function that customizes sensor fusion to match the network and sensor distribution characteristics, enhancing adaptability. To address the energy constraints of sensors, we utilize memristors, known for their energy-efficient in-memory computing, enabling analog-domain computations that reduce energy use and computational overhead in edge computing. This dual approach of memristors and $L_p$-norm inspired sensor fusion fosters energy-efficient computational and transmission paradigms and serves as a practical energy-efficient solution with minimal performance loss.
Authors: James Wang, Bruce D. Lee, Ingvar Ziemann, Nikolai Matni
Abstract: We address the problem of learning to control an unknown nonlinear dynamical system through sequential interactions. Motivated by high-stakes applications in which mistakes can be catastrophic, such as robotics and healthcare, we study situations where it is possible for fast sequential learning to occur. Fast sequential learning is characterized by the ability of the learning agent to incur logarithmic regret relative to a fully-informed baseline. We demonstrate that fast sequential learning is achievable in a diverse class of continuous control problems where the system dynamics depend smoothly on unknown parameters, provided the optimal control policy is persistently exciting. Additionally, we derive a regret bound which grows with the square root of the number of interactions for cases where the optimal policy is not persistently exciting. Our results provide the first regret bounds for controlling nonlinear dynamical systems depending nonlinearly on unknown parameters. We validate the trends our theory predicts in simulation on a simple dynamical system.
Authors: Jean-Baptiste Guimbaud, Marc Plantevit, L\'ea Ma\^itre, R\'emy Cazabet
Abstract: In epidemiology, traditional statistical methods such as logistic regression, linear regression, and other parametric models are commonly employed to investigate associations between predictors and health outcomes. However, non-parametric machine learning techniques, such as deep neural networks (DNNs), coupled with explainable AI (XAI) tools, offer new opportunities for this task. Despite their potential, these methods face challenges due to the limited availability of high-quality, high-quantity data in this field. To address these challenges, we introduce SEANN, a novel approach for informed DNNs that leverages a prevalent form of domain-specific knowledge: Pooled Effect Sizes (PES). PESs are commonly found in published Meta-Analysis studies, in different forms, and represent a quantitative form of a scientific consensus. By direct integration within the learning procedure using a custom loss, we experimentally demonstrate significant improvements in the generalizability of predictive performances and the scientific plausibility of extracted relationships compared to a domain-knowledge agnostic neural network in a scarce and noisy data setting.
Authors: Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
Abstract: Multi-armed bandits (MAB) are commonly used in sequential online decision-making when the reward of each decision is an unknown random variable. In practice however, the typical goal of maximizing total reward may be less important than minimizing the total cost of the decisions taken, subject to a reward constraint. For example, we may seek to make decisions that have at least the reward of a reference ``default'' decision, with as low a cost as possible. This problem was recently introduced in the Multi-Armed Bandits with Cost Subsidy (MAB-CS) framework. MAB-CS is broadly applicable to problem domains where a primary metric (cost) is constrained by a secondary metric (reward), and the rewards are unknown. In our work, we address variants of MAB-CS including ones with reward constrained by the reward of a known reference arm or by the subsidized best reward. We introduce the Pairwise-Elimination (PE) algorithm for the known reference arm variant and generalize PE to PE-CS for the subsidized best reward variant. Our instance-dependent analysis of PE and PE-CS reveals that both algorithms have an order-wise logarithmic upper bound on Cost and Quality Regret, making our policies the first with such a guarantee. Moreover, by comparing our upper and lower bound results we establish that PE is order-optimal for all known reference arm problem instances. Finally, experiments are conducted using the MovieLens 25M and Goodreads datasets for both PE and PE-CS revealing the effectiveness of PE and the superior balance between performance and reliability offered by PE-CS compared to baselines from the literature.
Authors: Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
Abstract: Machine learning (ML) has the potential to revolutionize healthcare, but its adoption is often hindered by the disconnect between the needs of domain experts and translating these needs into robust and valid ML tools. Despite recent advances in LLM-based co-pilots to democratize ML for non-technical domain experts, these systems remain predominantly focused on model-centric aspects while overlooking critical data-centric challenges. This limitation is problematic in complex real-world settings where raw data often contains complex issues, such as missing values, label noise, and domain-specific nuances requiring tailored handling. To address this we introduce CliMB-DC, a human-guided, data-centric framework for LLM co-pilots that combines advanced data-centric tools with LLM-driven reasoning to enable robust, context-aware data processing. At its core, CliMB-DC introduces a novel, multi-agent reasoning system that combines a strategic coordinator for dynamic planning and adaptation with a specialized worker agent for precise execution. Domain expertise is then systematically incorporated to guide the reasoning process using a human-in-the-loop approach. To guide development, we formalize a taxonomy of key data-centric challenges that co-pilots must address. Thereafter, to address the dimensions of the taxonomy, we integrate state-of-the-art data-centric tools into an extensible, open-source architecture, facilitating the addition of new tools from the research community. Empirically, using real-world healthcare datasets we demonstrate CliMB-DC's ability to transform uncurated datasets into ML-ready formats, significantly outperforming existing co-pilot baselines for handling data-centric challenges. CliMB-DC promises to empower domain experts from diverse domains -- healthcare, finance, social sciences and more -- to actively participate in driving real-world impact using ML.
Authors: Andrea Avogaro, Luigi Capogrosso, Andrea Toaiari, Franco Fummi, Marco Cristani
Abstract: The fast fashion industry's insatiable demand for new styles and rapid production cycles has led to a significant environmental burden. Overproduction, excessive waste, and harmful chemicals have contributed to the negative environmental impact of the industry. To mitigate these issues, a paradigm shift that prioritizes sustainability and efficiency is urgently needed. Integrating learning-based predictive analytics into the fashion industry represents a significant opportunity to address environmental challenges and drive sustainable practices. By forecasting fashion trends and optimizing production, brands can reduce their ecological footprint while remaining competitive in a rapidly changing market. However, one of the key challenges in forecasting fashion sales is the dynamic nature of consumer preferences. Fashion is acyclical, with trends constantly evolving and resurfacing. In addition, cultural changes and unexpected events can disrupt established patterns. This problem is also known as New Fashion Products Performance Forecasting (NFPPF), and it has recently gained more and more interest in the global research landscape. Given its multidisciplinary nature, the field of NFPPF has been approached from many different angles. This comprehensive survey wishes to provide an up-to-date overview that focuses on learning-based NFPPF strategies. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing for a systematic and complete literature review. In particular, we propose the first taxonomy that covers the learning panorama for NFPPF, examining in detail the different methodologies used to increase the amount of multimodal information, as well as the state-of-the-art available datasets. Finally, we discuss the challenges and future directions.
Authors: Mohammed Guhdar, Ramadhan J. Mstafa, Abdulhakeem O. Mohammed
Abstract: Epilepsy is a prevalent neurological disorder globally, impacting around 50 million people \cite{WHO_epilepsy_50million}. Epileptic seizures result from sudden abnormal electrical activity in the brain, which can be read as sudden and significant changes in the EEG signal of the brain. The signal can vary in severity and frequency, which results in loss of consciousness and muscle contractions for a short period of time \cite{epilepsyfoundation_myoclonic}. Individuals with epilepsy often face significant employment challenges due to safety concerns in certain work environments. Many jobs that involve working at heights, operating heavy machinery, or in other potentially hazardous settings may be restricted for people with seizure disorders. This certainly limits job options and economic opportunities for those living with epilepsy.
Authors: Chao Feng, Nicolas Fazli Kohler, Alberto Huertas Celdran, Gerome Bovet, Burkhard Stiller
Abstract: The integration of Federated Learning (FL) and Multi-Task Learning (MTL) has been explored to address client heterogeneity, with Federated Multi-Task Learning (FMTL) treating each client as a distinct task. However, most existing research focuses on data heterogeneity (e.g., addressing non-IID data) rather than task heterogeneity, where clients solve fundamentally different tasks. Additionally, much of the work relies on centralized settings with a server managing the federation, leaving the more challenging domain of decentralized FMTL largely unexplored. Thus, this work bridges this gap by proposing ColNet, a framework designed for heterogeneous tasks in decentralized federated environments. ColNet divides models into the backbone and task-specific layers, forming groups of similar clients, with group leaders performing conflict-averse cross-group aggregation. A pool of experiments with different federations demonstrated ColNet outperforms the compared aggregation schemes in decentralized settings with label and task heterogeneity scenarios.
Authors: Zizhou Zhang, Xinshi Li, Yu Cheng, Zhenrui Chen, Qianying Liu
Abstract: Credit risk management within supply chains has emerged as a critical research area due to its significant implications for operational stability and financial sustainability. The intricate interdependencies among supply chain participants mean that credit risks can propagate across networks, with impacts varying by industry. This study explores the application of Generative Adversarial Networks (GANs) to enhance credit risk identification in supply chains. GANs enable the generation of synthetic credit risk scenarios, addressing challenges related to data scarcity and imbalanced datasets. By leveraging GAN-generated data, the model improves predictive accuracy while effectively capturing dynamic and temporal dependencies in supply chain data. The research focuses on three representative industries-manufacturing (steel), distribution (pharmaceuticals), and services (e-commerce) to assess industry-specific credit risk contagion. Experimental results demonstrate that the GAN-based model outperforms traditional methods, including logistic regression, decision trees, and neural networks, achieving superior accuracy, recall, and F1 scores. The findings underscore the potential of GANs in proactive risk management, offering robust tools for mitigating financial disruptions in supply chains. Future research could expand the model by incorporating external market factors and supplier relationships to further enhance predictive capabilities. Keywords- Generative Adversarial Networks (GANs); Supply Chain Risk; Credit Risk Identification; Machine Learning; Data Augmentation
Authors: Zekun Xi, Wenbiao Yin, Jizhan Fang, Jialong Wu, Runnan Fang, Ningyu Zhang, Jiang Yong, Pengjun Xie, Fei Huang, Huajun Chen
Abstract: Machine writing with large language models often relies on retrieval-augmented generation. However, these approaches remain confined within the boundaries of the model's predefined scope, limiting the generation of content with rich information. Specifically, vanilla-retrieved information tends to lack depth, utility, and suffers from redundancy, which negatively impacts the quality of generated articles, leading to shallow, repetitive, and unoriginal outputs. To address these issues, we propose OmniThink, a machine writing framework that emulates the human-like process of iterative expansion and reflection. The core idea behind OmniThink is to simulate the cognitive behavior of learners as they progressively deepen their knowledge of the topics. Experimental results demonstrate that OmniThink improves the knowledge density of generated articles without compromising metrics such as coherence and depth. Human evaluations and expert feedback further highlight the potential of OmniThink to address real-world challenges in the generation of long-form articles.
Authors: Yuxi Hong
Abstract: Accurate stock market prediction provides great opportunities for informed decision-making, yet existing methods struggle with financial data's non-linear, high-dimensional, and volatile characteristics. Advanced predictive models are needed to effectively address these complexities. This paper proposes a novel multi-layer hybrid multi-task learning (MTL) framework aimed at achieving more efficient stock market predictions. It involves a Transformer encoder to extract complex correspondences between various input features, a Bidirectional Gated Recurrent Unit (BiGRU) to capture long-term temporal relationships, and a Kolmogorov-Arnold Network (KAN) to enhance the learning process. Experimental evaluations indicate that the proposed learning structure achieves great performance, with an MAE as low as 1.078, a MAPE as low as 0.012, and an R^2 as high as 0.98, when compared with other competitive networks.
Authors: Nasim Soltani, Michael Loehning, Kaushik Chowdhury
Abstract: Artificial Intelligence (AI)-native receivers prove significant performance improvement in high noise regimes and can potentially reduce communication overhead compared to the traditional receiver. However, their performance highly depends on the representativeness of the training dataset. A major issue is the uncertainty of whether the training dataset covers all test environments and waveform configurations, and thus, whether the trained model is robust in practical deployment conditions. To this end, we propose a joint measurement-recovery framework for AI-native transceivers post deployment, called VERITAS, that continuously looks for distribution shifts in the received signals and triggers finite re-training spurts. VERITAS monitors the wireless channel using 5G pilots fed to an auxiliary neural network that detects out-of-distribution channel profile, transmitter speed, and delay spread. As soon as such a change is detected, a traditional (reference) receiver is activated, which runs for a period of time in parallel to the AI-native receiver. Finally, VERTIAS compares the bit probabilities of the AI-native and the reference receivers for the same received data inputs, and decides whether or not a retraining process needs to be initiated. Our evaluations reveal that VERITAS can detect changes in the channel profile, transmitter speed, and delay spread with 99%, 97%, and 69% accuracies, respectively, followed by timely initiation of retraining for 86%, 93.3%, and 94.8% of inputs in channel profile, transmitter speed, and delay spread test sets, respectively.
Authors: Yirong Zeng, Xiao Ding, Yuxian Wang, Weiwen Liu, Wu Ning, Yutai Hou, Xu Huang, Bing Qin, Ting Liu
Abstract: Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities. Effectively leveraging this potential for complex tasks hinges crucially on improving their ability to use tools. Synthesizing tool use data by simulating the real world is an effective approach. Nevertheless, our investigation reveals that training gains significantly decay as the scale of these data increases. The primary factor is the model's poor performance (a.k.a deficiency) in complex scenarios, which hinders learning from data using SFT. Driven by this objective, we propose an iterative reinforced fine-tuning strategy to continually guide the model to alleviate it. Specifically, we first identify deficiency-related data based on feedback from the policy model, then perform a Monte Carlo Tree Search to collect fine-grained preference pairs to pinpoint deficiencies. Subsequently, we update the policy model using preference optimization to align with ground truth and misalign with deficiencies. This process can be iterated. Moreover, before the iteration, we propose an easy-to-hard warm-up SFT strategy to facilitate learning from challenging data. The experiments demonstrate our models go beyond the same parametric models, outperforming many larger open-source and closed-source models. Additionally, it has achieved notable training gains in complex tool use scenarios.
Authors: Wonjun Lee, Riley C. W. O'Neill, Dongmian Zou, Jeff Calder, Gilad Lerman
Abstract: Generative modeling aims to generate new data samples that resemble a given dataset, with diffusion models recently becoming the most popular generative model. One of the main challenges of diffusion models is solving the problem in the input space, which tends to be very high-dimensional. Recently, solving diffusion models in the latent space through an encoder that maps from the data space to a lower-dimensional latent space has been considered to make the training process more efficient and has shown state-of-the-art results. The variational autoencoder (VAE) is the most commonly used encoder/decoder framework in this domain, known for its ability to learn latent representations and generate data samples. In this paper, we introduce a novel encoder/decoder framework with theoretical properties distinct from those of the VAE, specifically designed to preserve the geometric structure of the data distribution. We demonstrate the significant advantages of this geometry-preserving encoder in the training process of both the encoder and decoder. Additionally, we provide theoretical results proving convergence of the training process, including convergence guarantees for encoder training, and results showing faster convergence of decoder training when using the geometry-preserving encoder.
Authors: Jingchen Sun, Shaobo Han, Wataru Kohno, Changyou Chen
Abstract: Contrastive Language-Audio Pretraining (CLAP) models have demonstrated unprecedented performance in various acoustic signal recognition tasks. Fiber-optic-based acoustic recognition is one of the most important downstream tasks and plays a significant role in environmental sensing. Adapting CLAP for fiber-optic acoustic recognition has become an active research area. As a non-conventional acoustic sensor, fiber-optic acoustic recognition presents a challenging, domain-specific, low-shot deployment environment with significant domain shifts due to unique frequency response and noise characteristics. To address these challenges, we propose a support-based adaptation method, CLAP-S, which linearly interpolates a CLAP Adapter with the Support Set, leveraging both implicit knowledge through fine-tuning and explicit knowledge retrieved from memory for cross-domain generalization. Experimental results show that our method delivers competitive performance on both laboratory-recorded fiber-optic ESC-50 datasets and a real-world fiber-optic gunshot-firework dataset. Our research also provides valuable insights for other downstream acoustic recognition tasks. The code and gunshot-firework dataset are available at https://github.com/Jingchensun/clap-s.
Authors: Bowen Wen, Matthew Trepte, Joseph Aribido, Jan Kautz, Orazio Gallo, Stan Birchfield
Abstract: Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline to remove ambiguous samples. We then design a number of network architecture components to enhance scalability, including a side-tuning feature backbone that adapts rich monocular priors from vision foundation models to mitigate the sim-to-real gap, and long-range context reasoning for effective cost volume filtering. Together, these components lead to strong robustness and accuracy across domains, establishing a new standard in zero-shot stereo depth estimation.
Authors: Stamatina Lamprinakou, Huiyan Sang, Bledar A. Konomi, Ligang Lu
Abstract: Bayesian Additive Regression Trees [BART, Chipman et al., 2010] have gained significant popularity due to their remarkable predictive performance and ability to quantify uncertainty. However, standard decision tree models rely on recursive data splits at each decision node, using deterministic decision rules based on a single univariate feature. This approach limits their ability to effectively capture complex decision boundaries, particularly in scenarios involving multiple features, such as spatial domains, or when transitions are either sharp or smoothly varying. In this paper, we introduce a novel probabilistic additive decision tree model that employs a soft split rule. This method enables highly flexible splits that leverage both univariate and multivariate features, while also respecting the geometric properties of the feature domain. Notably, the probabilistic split rule adapts dynamically across decision nodes, allowing the model to account for varying levels of smoothness in the regression function. We demonstrate the utility of the proposed model through comparisons with existing tree-based models on synthetic datasets and a New York City education dataset.
Authors: Haichao Zhang, Haonan Yu, Le Zhao, Andrew Choi, Qinxun Bai, Yiqing Yang, Wei Xu
Abstract: We present a low-cost quadruped manipulation system that solves long-horizon real-world tasks, trained by reinforcement learning purely in simulation. The system comprises 1) a hierarchical design of a high-level policy for visual-mobile manipulation following instructions, and a low-level policy for quadruped movement and limb-control, 2) a progressive policy expansion approach for solving the long-horizon task together with a teacher-student framework for efficient high-level training of the high-level visuomotor policy, and 3) a suite of techniques for minimizing sim-to-real gaps. With budget-friendly but limited reliability and performance hardware, and just one wrist-mounted RGB camera, the entire system fully trained in simulation achieves high success rates for long horizon tasks involving search, move, grasp, and drop-into, with fluid sim-to-real transfer in a wide variety of indoor and outdoor scenes and lighting conditions.Extensive real-world evaluations show that on the long horizon mobile manipulation tasks, our system achieves good performance when transferred to real both in terms of task success rate and execution efficiency. Finally, we discuss the necessity of our sim-to-real techniques for legged mobile manipulation, and show their ablation performance.
Authors: Duong Tan Loc, Nguyen Thang Loi, Vo Nguyen Le Duy
Abstract: In high-dimensional regression, feature selection methods, such as sequential feature selection (SeqFS), are commonly used to identify relevant features. When data is limited, domain adaptation (DA) becomes crucial for transferring knowledge from a related source domain to a target domain, improving generalization performance. Although SeqFS after DA is an important task in machine learning, none of the existing methods can guarantee the reliability of its results. In this paper, we propose a novel method for testing the features selected by SeqFS-DA. The main advantage of the proposed method is its capability to control the false positive rate (FPR) below a significance level $\alpha$ (e.g., 0.05). Additionally, a strategic approach is introduced to enhance the statistical power of the test. Furthermore, we provide extensions of the proposed method to SeqFS with model selection criteria including AIC, BIC, and adjusted R-squared. Extensive experiments are conducted on both synthetic and real-world datasets to validate the theoretical results and demonstrate the proposed method's superior performance.
Authors: Sajjad Saleem, Adil Hussain, Nabila Majeed, Zahid Akhtar, Kamran Siddique
Abstract: Wheat is an important source of dietary fiber and protein that is negatively impacted by a number of risks to its growth. The difficulty of identifying and classifying wheat diseases is discussed with an emphasis on wheat loose smut, leaf rust, and crown and root rot. Addressing conditions like crown and root rot, this study introduces an innovative approach that integrates multi-scale feature extraction with advanced image segmentation techniques to enhance classification accuracy. The proposed method uses neural network models Xception, Inception V3, and ResNet 50 to train on a large wheat disease classification dataset 2020 in conjunction with an ensemble of machine vision classifiers, including voting and stacking. The study shows that the suggested methodology has a superior accuracy of 99.75% in the classification of wheat diseases when compared to current state-of-the-art approaches. A deep learning ensemble model Xception showed the highest accuracy.
Authors: Xigui Li, Yuanye Zhou, Feiyang Xiao, Xin Guo, Yichi Zhang, Chen Jiang, Jianchao Ge, Xiansheng Wang, Qimeng Wang, Taiwei Zhang, Chensen Lin, Yuan Cheng, Yuan Qi
Abstract: Intracranial aneurysm (IA) is a common cerebrovascular disease that is usually asymptomatic but may cause severe subarachnoid hemorrhage (SAH) if ruptured. Although clinical practice is usually based on individual factors and morphological features of the aneurysm, its pathophysiology and hemodynamic mechanisms remain controversial. To address the limitations of current research, this study constructed a comprehensive hemodynamic dataset of intracranial aneurysms. The dataset is based on 466 real aneurysm models, and 10,000 synthetic models were generated by resection and deformation operations, including 466 aneurysm-free models and 9,534 deformed aneurysm models. The dataset also provides medical image-like segmentation mask files to support insightful analysis. In addition, the dataset contains hemodynamic data measured at eight steady-state flow rates (0.001 to 0.004 kg/s), including critical parameters such as flow velocity, pressure, and wall shear stress, providing a valuable resource for investigating aneurysm pathogenesis and clinical prediction. This dataset will help advance the understanding of the pathologic features and hemodynamic mechanisms of intracranial aneurysms and support in-depth research in related fields. Dataset hosted at https://github.com/Xigui-Li/Aneumo.
Authors: Yuefan Cao, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song
Abstract: Text-to-video generation models have made impressive progress, but they still struggle with generating videos with complex features. This limitation often arises from the inability of the text encoder to produce accurate embeddings, which hinders the video generation model. In this work, we propose a novel approach to overcome this challenge by selecting the optimal text embedding through interpolation in the embedding space. We demonstrate that this method enables the video generation model to produce the desired videos. Additionally, we introduce a simple algorithm using perpendicular foot embeddings and cosine similarity to identify the optimal interpolation embedding. Our findings highlight the importance of accurate text embeddings and offer a pathway for improving text-to-video generation performance.
Authors: Hildo Bijl
Abstract: The field of Knowledge Tracing is focused on predicting the success rate of a student for a given skill. Modern methods like Deep Knowledge Tracing provide accurate estimates given enough data, but being based on neural networks they struggle to explain how these estimates are formed. More classical methods like Dynamic Bayesian Networks can do this, but they cannot give data on the accuracy of their estimates and often struggle to incorporate new observations in real-time due to their high computational load. This paper presents a novel method, Performance Distribution Tracing (PDT), in which the distribution of the success rate is traced live. It uses a Dynamic Bayesian Network with continuous random variables as nodes. By tracing the success rate distribution, there is always data available on the accuracy of any success rate estimation. In addition, it makes it possible to combine data from similar/related skills to come up with a more informed estimate of success rates. This makes it possible to predict exercise success rates, providing both explainability and an accuracy indication, even when an exercise requires a combination of different skills to solve. And through the use of the beta distribution functions as conjugate priors, all distributions are available in analytical form, allowing efficient online updates upon new observations. Experiments have shown that the resulting estimates generally feel sufficiently accurate to end-users such that they accept recommendations based on them.
Authors: Keita Miwa, Kento Sasaki, Hidehisa Arai, Tsubasa Takahashi, Yu Yamaguchi
Abstract: Current image tokenization methods require a large number of tokens to capture the information contained within images. Although the amount of information varies across images, most image tokenizers only support fixed-length tokenization, leading to inefficiency in token allocation. In this study, we introduce One-D-Piece, a discrete image tokenizer designed for variable-length tokenization, achieving quality-controllable mechanism. To enable variable compression rate, we introduce a simple but effective regularization mechanism named "Tail Token Drop" into discrete one-dimensional image tokenizers. This method encourages critical information to concentrate at the head of the token sequence, enabling support of variadic tokenization, while preserving state-of-the-art reconstruction quality. We evaluate our tokenizer across multiple reconstruction quality metrics and find that it delivers significantly better perceptual quality than existing quality-controllable compression methods, including JPEG and WebP, at smaller byte sizes. Furthermore, we assess our tokenizer on various downstream computer vision tasks, including image classification, object detection, semantic segmentation, and depth estimation, confirming its adaptability to numerous applications compared to other variable-rate methods. Our approach demonstrates the versatility of variable-length discrete image tokenization, establishing a new paradigm in both compression efficiency and reconstruction performance. Finally, we validate the effectiveness of tail token drop via detailed analysis of tokenizers.
Authors: Ali Can Karaca, M. Enes Ozelbas, Saadettin Berber, Orkhan Karimli, Turabi Yildirim, M. Fatih Amasyali
Abstract: Remote sensing change captioning (RSICC) aims to describe changes between bitemporal images in natural language. Existing methods often fail under challenges like illumination differences, viewpoint changes, blur effects, leading to inaccuracies, especially in no-change regions. Moreover, the images acquired at different spatial resolutions and have registration errors tend to affect the captions. To address these issues, we introduce SECOND-CC, a novel RSICC dataset featuring high-resolution RGB image pairs, semantic segmentation maps, and diverse real-world scenarios. SECOND-CC which contains 6,041 pairs of bitemporal RS images and 30,205 sentences describing the differences between images. Additionally, we propose MModalCC, a multimodal framework that integrates semantic and visual data using advanced attention mechanisms, including Cross-Modal Cross Attention (CMCA) and Multimodal Gated Cross Attention (MGCA). Detailed ablation studies and attention visualizations further demonstrate its effectiveness and ability to address RSICC challenges. Comprehensive experiments show that MModalCC outperforms state-of-the-art RSICC methods, including RSICCformer, Chg2Cap, and PSNet with +4.6% improvement on BLEU4 score and +9.6% improvement on CIDEr score. We will make our dataset and codebase publicly available to facilitate future research at https://github.com/ChangeCapsInRS/SecondCC
Authors: Marie Kempkes, Aroosa Ijaz, Elies Gil-Fuster, Carlos Bravo-Prieto, Jakob Spiegelberg, Evert van Nieuwenburg, Vedran Dunjko
Abstract: The double descent phenomenon challenges traditional statistical learning theory by revealing scenarios where larger models do not necessarily lead to reduced performance on unseen data. While this counterintuitive behavior has been observed in a variety of classical machine learning models, particularly modern neural network architectures, it remains elusive within the context of quantum machine learning. In this work, we analytically demonstrate that quantum learning models can exhibit double descent behavior by drawing on insights from linear regression and random matrix theory. Additionally, our numerical experiments on quantum kernel methods across different real-world datasets and system sizes further confirm the existence of a test error peak, a characteristic feature of double descent. Our findings provide evidence that quantum models can operate in the modern, overparameterized regime without experiencing overfitting, thereby opening pathways to improved learning performance beyond traditional statistical learning theory.
Authors: Jef Jonkers, Luc Duchateau, Glenn Van Wallendael, Sofie Van Hoecke
Abstract: Anatomical landmark localization in 2D/3D images is a critical task in medical imaging. Although many general-purpose tools exist for landmark localization in classical computer vision tasks, such as pose estimation, they lack the specialized features and modularity necessary for anatomical landmark localization applications in the medical domain. Therefore, we introduce landmarker, a Python package built on PyTorch. The package provides a comprehensive, flexible toolkit for developing and evaluating landmark localization algorithms, supporting a range of methodologies, including static and adaptive heatmap regression. landmarker enhances the accuracy of landmark identification, streamlines research and development processes, and supports various image formats and preprocessing pipelines. Its modular design allows users to customize and extend the toolkit for specific datasets and applications, accelerating innovation in medical imaging. landmarker addresses a critical need for precision and customization in landmark localization tasks not adequately met by existing general-purpose pose estimation tools.
Authors: Chenhao Li, Andreas Krause, Marco Hutter
Abstract: Learning robust and generalizable world models is crucial for enabling efficient and scalable robotic control in real-world environments. In this work, we introduce a novel framework for learning world models that accurately capture complex, partially observable, and stochastic dynamics. The proposed method employs a dual-autoregressive mechanism and self-supervised training to achieve reliable long-horizon predictions without relying on domain-specific inductive biases, ensuring adaptability across diverse robotic tasks. We further propose a policy optimization framework that leverages world models for efficient training in imagined environments and seamless deployment in real-world systems. Through extensive experiments, our approach consistently outperforms state-of-the-art methods, demonstrating superior autoregressive prediction accuracy, robustness to noise, and generalization across manipulation and locomotion tasks. Notably, policies trained with our method are successfully deployed on ANYmal D hardware in a zero-shot transfer, achieving robust performance with minimal sim-to-real performance loss. This work advances model-based reinforcement learning by addressing the challenges of long-horizon prediction, error accumulation, and sim-to-real transfer. By providing a scalable and robust framework, the introduced methods pave the way for adaptive and efficient robotic systems in real-world applications.
Authors: Yichen He, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, Weinan E
Abstract: We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholarly queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academic queries to assess PaSa performance in more realistic scenarios. Despite being trained on synthetic data, PaSa significantly outperforms existing baselines on RealScholarQuery, including Google, Google Scholar, Google with GPT-4 for paraphrased queries, chatGPT (search-enabled GPT-4o), GPT-o1, and PaSa-GPT-4o (PaSa implemented by prompting GPT-4o). Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37.78% in recall@20 and 39.90% in recall@50. It also exceeds PaSa-GPT-4o by 30.36% in recall and 4.25% in precision. Model, datasets, and code are available at https://github.com/bytedance/pasa.
Authors: Abhishek Kaushik (School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Co. Louth, Ireland), Sargam Yadav (School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Co. Louth, Ireland), Andrew Browne (Dublin Business School, Dublin, Co. Dublin, Ireland), David Lillis (University College Dublin, Belfield, Dublin, Co. Dublin, Ireland), David Williams (Dublin Business School, Dublin, Co. Dublin, Ireland), Jack Mc Donnell (School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Co. Louth, Ireland), Peadar Grant (School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Co. Louth, Ireland), Siobhan Connolly Kernan (School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Co. Louth, Ireland), Shubham Sharma (Technological University Dublin, Dublin, Co. Dublin, Ireland), Mansi Arora (Jagan Institute of Management Studies, Rohini, Delhi, Delhi, India)
Abstract: The recent advancements in Generative Artificial intelligence (GenAI) technology have been transformative for the field of education. Large Language Models (LLMs) such as ChatGPT and Bard can be leveraged to automate boilerplate tasks, create content for personalised teaching, and handle repetitive tasks to allow more time for creative thinking. However, it is important to develop guidelines, policies, and assessment methods in the education sector to ensure the responsible integration of these tools. In this article, thematic analysis has been performed on seven essays obtained from professionals in the education sector to understand the advantages and pitfalls of using GenAI models such as ChatGPT and Bard in education. Exploratory Data Analysis (EDA) has been performed on the essays to extract further insights from the text. The study found several themes which highlight benefits and drawbacks of GenAI tools, as well as suggestions to overcome these limitations and ensure that students are using these tools in a responsible and ethical manner.
Authors: Shuangjiang Xue, Pierre Le Bras, David A. Robb, Mike J. Chantler, Stefano Padilla
Abstract: Stopword removal is a critical stage in many Machine Learning methods but often receives little consideration, it interferes with the model visualizations and disrupts user confidence. Inappropriately chosen or hastily omitted stopwords not only lead to suboptimal performance but also significantly affect the quality of models, thus reducing the willingness of practitioners and stakeholders to rely on the output visualizations. This paper proposes a novel extraction method that provides a corpus-specific probabilistic estimation of stopword likelihood and an interactive visualization system to support their analysis. We evaluated our approach and interface using real-world data, a commonly used Machine Learning method (Topic Modelling), and a comprehensive qualitative experiment probing user confidence. The results of our work show that our system increases user confidence in the credibility of topic models by (1) returning reasonable probabilities, (2) generating an appropriate and representative extension of common stopword lists, and (3) providing an adjustable threshold for estimating and analyzing stopwords visually. Finally, we discuss insights, recommendations, and best practices to support practitioners while improving the output of Machine Learning methods and topic model visualizations with robust stopword analysis and removal.
Authors: Alexandre Caboussat, Anna Peruso
Abstract: Optimal transportation of raw material from suppliers to customers is an issue arising in logistics that is addressed here with a continuous model relying on optimal transport theory. A physics informed neuralnetwork method is advocated here for the solution of the corresponding generalized Monge-Amp`ere equation. Convex neural networks are advocated to enforce the convexity of the solution to the Monge-Amp\`ere equation and obtain a suitable approximation of the optimal transport map. A particular focus is set on the enforcement of transport boundary conditions in the loss function. Numerical experiments illustrate the solution to the optimal transport problem in several configurations, and sensitivity analyses are performed.
Authors: Kazuma Onishi, Katsuhiko Hayashi
Abstract: Extreme multi-label learning (XML) is a task of assigning multiple labels from an extremely large set of labels to each data instance. Many current high-performance XML models are composed of a lot of hyperparameters, which complicates the tuning process. Additionally, the models themselves are adapted specifically to XML, which complicates their reimplementation. To remedy this problem, we propose a simple method based on ridge regression for XML. The proposed method not only has a closed-form solution but also is composed of a single hyperparameter. Since there are no precedents on applying ridge regression to XML, this paper verified the performance of the method by using various XML benchmark datasets. Furthermore, we enhanced the prediction of low-frequency labels in XML, which hold informative content. This prediction is essential yet challenging because of the limited amount of data. Here, we employed a simple frequency-based weighting. This approach greatly simplifies the process compared with existing techniques. Experimental results revealed that it can achieve levels of performance comparable to, or even exceeding, those of models with numerous hyperparameters. Additionally, we found that the frequency-based weighting significantly improved the predictive performance for low-frequency labels, while requiring almost no changes in implementation. The source code for the proposed method is available on github at https://github.com/cars1015/XML-ridge.
Authors: Marius Potfer, Dorian Baudry, Hugo Richard, Vianney Perchet, Cheng Wan
Abstract: Motivated by the strategic participation of electricity producers in electricity day-ahead market, we study the problem of online learning in repeated multi-unit uniform price auctions focusing on the adversarial opposing bid setting. The main contribution of this paper is the introduction of a new modeling of the bid space. Indeed, we prove that a learning algorithm leveraging the structure of this problem achieves a regret of $\tilde{O}(K^{4/3}T^{2/3})$ under bandit feedback, improving over the bound of $\tilde{O}(K^{7/4}T^{3/4})$ previously obtained in the literature. This improved regret rate is tight up to logarithmic terms. Inspired by electricity reserve markets, we further introduce a different feedback model under which all winning bids are revealed. This feedback interpolates between the full-information and bandit scenarios depending on the auctions' results. We prove that, under this feedback, the algorithm that we propose achieves regret $\tilde{O}(K^{5/2}\sqrt{T})$.
Authors: M. A. Maia, I. B. C. M. Rocha, D. Kova\v{c}evi\'c, F. P. van der Meer
Abstract: In this paper, we present a surrogate-based multiscale approach to model constant strain-rate and creep experiments on unidirectional thermoplastic composites under off-axis loading. In previous contributions, these experiments were modeled through a single-scale micromechanical simulation under the assumption of macroscopic homogeneity. Although efficient and accurate in many scenarios, simulations with low-off axis angles showed significant discrepancies with the experiments. It was hypothesized that the mismatch was caused by macroscopic inhomogeneity, which would require a multiscale approach to capture it. However, full-field multiscale simulations remain computationally prohibitive. To address this issue, we replace the micromodel with a Physically Recurrent Neural Network (PRNN), a surrogate model that combines data-driven components with embedded constitutive models to capture history-dependent behavior naturally. The explainability of the latent space of this network is also explored in a transfer learning strategy that requires no re-training. With the surrogate-based simulations, we confirm the hypothesis raised on the inhomogeneity of the macroscopic strain field and gain insights into the influence of adjustment of the experimental setup with oblique end-tabs. Results from the surrogate-based multiscale approach show better agreement with experiments than the single-scale micromechanical approach over a wide range of settings, although with limited accuracy on the creep experiments, where macroscopic test effects were implicitly taken into account in the material properties calibration.
Authors: Christoph Jansen
Abstract: This habilitation thesis is cumulative and, therefore, is collecting and connecting research that I (together with several co-authors) have conducted over the last few years. Thus, the absolute core of the work is formed by the ten publications listed on page 5 under the name Contributions 1 to 10. The references to the complete versions of these articles are also found in this list, making them as easily accessible as possible for readers wishing to dive deep into the different research projects. The chapters following this thesis, namely Parts A to C and the concluding remarks, serve to place the articles in a larger scientific context, to (briefly) explain their respective content on a less formal level, and to highlight some interesting perspectives for future research in their respective contexts. Naturally, therefore, the following presentation has neither the level of detail nor the formal rigor that can (hopefully) be found in the papers. The purpose of the following text is to provide the reader an easy and high-level access to this interesting and important research field as a whole, thereby, advertising it to a broader audience.
Authors: Nicolas Atienza, Christophe Labreuche, Johanne Cohen, Michele Sebag
Abstract: This paper introduces a novel method, Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE), which transforms a classifier into an abstaining classifier, offering provable protection against out-of-distribution and adversarial samples. The approach is based on a Generalized Extreme Value (GEV) model of the training distribution in the classifier's latent space, enabling the formal characterization of OOD samples. Interestingly, under mild assumptions, the GEV model also allows for formally characterizing adversarial samples. The abstaining classifier, which rejects samples based on their assessment by the GEV model, provably avoids OOD and adversarial samples. The empirical validation of the approach, conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and medium and large-sized datasets (CIFAR-10, CIFAR-100, and ImageNet), demonstrates its frugality, stability, and efficiency compared to the state of the art.
Authors: Annita Vapsi, Andr\'es Mu\~noz, Nancy Thomas, Keshav Ramani, Daniel Borrajo
Abstract: Recent advances in the field of out-of-distribution (OOD) detection have placed great emphasis on learning better representations suited to this task. While there are distance-based approaches, distributional awareness has seldom been exploited for better performance. We present HAC$_k$-OOD, a novel OOD detection method that makes no distributional assumption about the data, but automatically adapts to its distribution. Specifically, HAC$_k$-OOD constructs a set of hypercones by maximizing the angular distance to neighbors in a given data-point's vicinity to approximate the contour within which in-distribution (ID) data-points lie. Experimental results show state-of-the-art FPR@95 and AUROC performance on Near-OOD detection and on Far-OOD detection on the challenging CIFAR-100 benchmark without explicitly training for OOD performance.
Authors: \v{S}imon Kucharsk\'y, Paul Christian B\"urkner
Abstract: Finite mixtures are a broad class of models useful in scenarios where observed data is generated by multiple distinct processes but without explicit information about the responsible process for each data point. Estimating Bayesian mixture models is computationally challenging due to issues such as high-dimensional posterior inference and label switching. Furthermore, traditional methods such as MCMC are applicable only if the likelihoods for each mixture component are analytically tractable. Amortized Bayesian Inference (ABI) is a simulation-based framework for estimating Bayesian models using generative neural networks. This allows the fitting of models without explicit likelihoods, and provides fast inference. ABI is therefore an attractive framework for estimating mixture models. This paper introduces a novel extension of ABI tailored to mixture models. We factorize the posterior into a distribution of the parameters and a distribution of (categorical) mixture indicators, which allows us to use a combination of generative neural networks for parameter inference, and classification networks for mixture membership identification. The proposed framework accommodates both independent and dependent mixture models, enabling filtering and smoothing. We validate and demonstrate our approach through synthetic and real-world datasets.
Authors: Karl El Hajal, Enno Hermann, Ajinkya Kulkarni, Mathew Magimai. -Doss
Abstract: Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcribed speech data to estimate speaking rates and phoneme durations, which might not be available for unseen speakers. Therefore, we combine unsupervised rhythm and voice conversion methods based on self-supervised speech representations to map dysarthric to typical speech. We evaluate the outputs with a large ASR model pre-trained on healthy speech without further fine-tuning and find that the proposed rhythm conversion especially improves performance for speakers of the Torgo corpus with more severe cases of dysarthria. Code and audio samples are available at https://idiap.github.io/RnV .
Authors: Mohammad Moshtaghifar, Anton Rodomanov, Daniil Vankov, Sebastian Stich
Abstract: We present a novel universal gradient method for solving convex optimization problems. Our algorithm -- Dual Averaging with Distance Adaptation (DADA) -- is based on the classical scheme of dual averaging and dynamically adjusts its coefficients based on observed gradients and the distance between iterates and the starting point, eliminating the need for problem-specific parameters. DADA is a universal algorithm that simultaneously works for a broad spectrum of problem classes, provided the local growth of the objective function around its minimizer can be bounded. Particular examples of such problem classes are nonsmooth Lipschitz functions, Lipschitz-smooth functions, H\"older-smooth functions, functions with high-order Lipschitz derivative, quasi-self-concordant functions, and $(L_0,L_1)$-smooth functions. Crucially, DADA is applicable to both unconstrained and constrained problems, even when the domain is unbounded, without requiring prior knowledge of the number of iterations or desired accuracy.
Authors: Pit Neitemeier, Bj\"orn Deiseroth, Constantin Eichenberg, Lukas Balles
Abstract: Tokenization is a fundamental step in natural language processing, breaking text into units that computational models can process. While learned subword tokenizers have become the de-facto standard, they present challenges such as large vocabularies, limited adaptability to new domains or languages, and sensitivity to spelling errors and variations. To overcome these limitations, we investigate a hierarchical architecture for autoregressive language modelling that combines character-level and word-level processing. It employs a lightweight character-level encoder to convert character sequences into word embeddings, which are then processed by a word-level backbone model and decoded back into characters via a compact character-level decoder. This method retains the sequence compression benefits of word-level tokenization without relying on a rigid, predefined vocabulary. We demonstrate, at scales up to 7 billion parameters, that hierarchical transformers match the downstream task performance of subword-tokenizer-based models while exhibiting significantly greater robustness to input perturbations. Additionally, during continued pretraining on an out-of-domain language, our model trains almost twice as fast, achieves superior performance on the target language, and retains more of its previously learned knowledge. Hierarchical transformers pave the way for NLP systems that are more robust, flexible, and generalizable across languages and domains.
Authors: Wenqian Jiang, Junyang Jin
Abstract: Diagnosis of ice accretion on wind turbine blades is all the time a hard nut to crack in condition monitoring of wind farms. Existing methods focus on mechanism analysis of icing process, deviation degree analysis of feature engineering. However, there have not been deep researches of neural networks applied in this field at present. Supervisory control and data acquisition (SCADA) makes it possible to train networks through continuously providing not only operation parameters and performance parameters of wind turbines but also environmental parameters and operation modes. This paper explores the possibility that using convolutional neural networks (CNNs), generative adversarial networks (GANs) and domain adaption learning to establish intelligent diagnosis frameworks under different training scenarios. Specifically, PGANC and PGANT are proposed for sufficient and non-sufficient target wind turbine labeled data, respectively. The basic idea is that we consider a two-stage training with parallel GANs, which are aimed at capturing intrinsic features for normal and icing samples, followed by classification CNN or domain adaption module in various training cases. Model validation on three wind turbine SCADA data shows that two-stage training can effectively improve the model performance. Besides, if there is no sufficient labeled data for a target turbine, which is an extremely common phenomenon in real industrial practices, the addition of domain adaption learning makes the trained model show better performance. Overall, our proposed intelligent diagnosis frameworks can achieve more accurate detection on the same wind turbine and more generalized capability on a new wind turbine, compared with other machine learning models and conventional CNNs.
Authors: Shenhao Wang, Baichuan Mo, Yunhan Zheng, Stephane Hess, Jinhua Zhao
Abstract: Numerous studies have compared machine learning (ML) and discrete choice models (DCMs) in predicting travel demand. However, these studies often lack generalizability as they compare models deterministically without considering contextual variations. To address this limitation, our study develops an empirical benchmark by designing a tournament model, thus efficiently summarizing a large number of experiments, quantifying the randomness in model comparisons, and using formal statistical tests to differentiate between the model and contextual effects. This benchmark study compares two large-scale data sources: a database compiled from literature review summarizing 136 experiments from 35 studies, and our own experiment data, encompassing a total of 6,970 experiments from 105 models and 12 model families. This benchmark study yields two key findings. Firstly, many ML models, particularly the ensemble methods and deep learning, statistically outperform the DCM family (i.e., multinomial, nested, and mixed logit models). However, this study also highlights the crucial role of the contextual factors (i.e., data sources, inputs and choice categories), which can explain models' predictive performance more effectively than the differences in model types alone. Model performance varies significantly with data sources, improving with larger sample sizes and lower dimensional alternative sets. After controlling all the model and contextual factors, significant randomness still remains, implying inherent uncertainty in such model comparisons. Overall, we suggest that future researchers shift more focus from context-specific model comparisons towards examining model transferability across contexts and characterizing the inherent uncertainty in ML, thus creating more robust and generalizable next-generation travel demand models.
Authors: Marc-Andr\'e Z\"oller, Fabian Mauthe, Peter Zeiler, Marius Lindauer, Marco F. Huber
Abstract: Being able to predict the remaining useful life (RUL) of an engineering system is an important task in prognostics and health management. Recently, data-driven approaches to RUL predictions are becoming prevalent over model-based approaches since no underlying physical knowledge of the engineering system is required. Yet, this just replaces required expertise of the underlying physics with machine learning (ML) expertise, which is often also not available. Automated machine learning (AutoML) promises to build end-to-end ML pipelines automatically enabling domain experts without ML expertise to create their own models. This paper introduces AutoRUL, an AutoML-driven end-to-end approach for automatic RUL predictions. AutoRUL combines fine-tuned standard regression methods to an ensemble with high predictive power. By evaluating the proposed method on eight real-world and synthetic datasets against state-of-the-art hand-crafted models, we show that AutoML provides a viable alternative to hand-crafted data-driven RUL predictions. Consequently, creating RUL predictions can be made more accessible for domain experts using AutoML by eliminating ML expertise from data-driven model construction.
Authors: Dominik Baumann, Erfaun Noorani, James Price, Ole Peters, Colm Connaughton, Thomas B. Sch\"on
Abstract: Envisioned application areas for reinforcement learning (RL) include autonomous driving, precision agriculture, and finance, which all require RL agents to make decisions in the real world. A significant challenge hindering the adoption of RL methods in these domains is the non-robustness of conventional algorithms. In particular, the focus of RL is typically on the expected value of the return. The expected value is the average over the statistical ensemble of infinitely many trajectories, which can be uninformative about the performance of the average individual. For instance, when we have a heavy-tailed return distribution, the ensemble average can be dominated by rare extreme events. Consequently, optimizing the expected value can lead to policies that yield exceptionally high returns with a probability that approaches zero but almost surely result in catastrophic outcomes in single long trajectories. In this paper, we develop an algorithm that lets RL agents optimize the long-term performance of individual trajectories. The algorithm enables the agents to learn robust policies, which we show in an instructive example with a heavy-tailed return distribution and standard RL benchmarks. The key element of the algorithm is a transformation that we learn from data. This transformation turns the time series of collected returns into one for whose increments expected value and the average over a long trajectory coincide. Optimizing these increments results in robust policies.
Authors: Freek Holvoet, Katrien Antonio, Roel Henckaerts
Abstract: Insurers usually turn to generalized linear models for modeling claim frequency and severity data. Due to their success in other fields, machine learning techniques are gaining popularity within the actuarial toolbox. Our paper contributes to the literature on frequency-severity insurance pricing with machine learning via deep learning structures. We present a benchmark study on four insurance data sets with frequency and severity targets in the presence of multiple types of input features. We compare in detail the performance of: a generalized linear model on binned input data, a gradient-boosted tree model, a feed-forward neural network (FFNN), and the combined actuarial neural network (CANN). The CANNs combine a baseline prediction established with a GLM and GBM, respectively, with a neural network correction. We explain the data preprocessing steps with specific focus on the multiple types of input features typically present in tabular insurance data sets, such as postal codes, numeric and categorical covariates. Autoencoders are used to embed the categorical variables into the neural network, and we explore their potential advantages in a frequency-severity setting. Model performance is evaluated not only on out-of-sample deviance but also using statistical and calibration performance criteria and managerial tools to get more nuanced insights. Finally, we construct global surrogate models for the neural nets' frequency and severity models. These surrogates enable the translation of the essential insights captured by the FFNNs or CANNs to GLMs. As such, a technical tariff table results that can easily be deployed in practice.
Authors: Kumar Krishna Agrawal, Arna Ghosh, Shagun Sodhani, Adam Oberman, Blake Richards
Abstract: Recent progress in self-supervised (SSL) visual representation learning has led to the development of several different proposed frameworks that rely on augmentations of images but use different loss functions. However, there are few theoretically grounded principles to guide practice, so practical implementation of each SSL framework requires several heuristics to achieve competitive performance. In this work, we build on recent analytical results to design practical recommendations for competitive and efficient SSL that are grounded in theory. Specifically, recent theory tells us that existing SSL frameworks are minimizing the same idealized loss, which is to learn features that best match the data similarity kernel defined by the augmentations used. We show how this idealized loss can be reformulated to a functionally equivalent loss that is more efficient to compute. We study the implicit bias of using gradient descent to minimize our reformulated loss function and find that using a stronger orthogonalization constraint with a reduced projector dimensionality should yield good representations. Furthermore, the theory tells us that approximating the reformulated loss should be improved by increasing the number of augmentations, and as such using multiple augmentations should lead to improved convergence. We empirically verify our findings on CIFAR, STL and Imagenet datasets, wherein we demonstrate an improved linear readout performance when training a ResNet-backbone using our theoretically grounded recommendations. Remarkably, we also demonstrate that by leveraging these insights, we can reduce the pretraining dataset size by up to 2$\times$ while maintaining downstream accuracy simply by using more data augmentations. Taken together, our work provides theoretically grounded recommendations that can be used to improve SSL convergence and efficiency.
Authors: Waris Gill (Virginia Tech), Ali Anwar (University of Minnesota Twin Cities), Muhammad Ali Gulzar (Virginia Tech)
Abstract: In Federated Learning, clients train models on local data and send updates to a central server, which aggregates them into a global model using a fusion algorithm. This collaborative yet privacy-preserving training comes at a cost. FL developers face significant challenges in attributing global model predictions to specific clients. Localizing responsible clients is a crucial step towards (a) excluding clients primarily responsible for incorrect predictions and (b) encouraging clients who contributed high-quality models to continue participating in the future. Existing ML debugging approaches are inherently inapplicable as they are designed for single-model, centralized training. We introduce TraceFL, a fine-grained neuron provenance capturing mechanism that identifies clients responsible for a global model's prediction by tracking the flow of information from individual clients to the global model. Since inference on different inputs activates a different set of neurons of the global model, TraceFL dynamically quantifies the significance of the global model's neurons in a given prediction, identifying the most crucial neurons in the global model. It then maps them to the corresponding neurons in every participating client to determine each client's contribution, ultimately localizing the responsible client. We evaluate TraceFL on six datasets, including two real-world medical imaging datasets and four neural networks, including advanced models such as GPT. TraceFL achieves 99% accuracy in localizing the responsible client in FL tasks spanning both image and text classification tasks. At a time when state-of-the-artML debugging approaches are mostly domain-specific (e.g., image classification only), TraceFL is the first technique to enable highly accurate automated reasoning across a wide range of FL applications.
Authors: Kaifeng Lyu, Haoyu Zhao, Xinran Gu, Dingli Yu, Anirudh Goyal, Sanjeev Arora
Abstract: Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datasets can give rise to unsafe behaviors in the models. The current paper is about methods and best practices to mitigate such loss of alignment. We focus on the setting where a public model is fine-tuned before serving users for specific usage, where the model should improve on the downstream task while maintaining alignment. Through extensive experiments on several chat models (Meta's Llama 2-Chat, Mistral AI's Mistral 7B Instruct v0.2, and OpenAI's GPT-3.5 Turbo), this paper uncovers that the prompt templates used during fine-tuning and inference play a crucial role in preserving safety alignment, and proposes the ``Pure Tuning, Safe Testing'' (PTST) strategy -- fine-tune models without a safety prompt, but include it at test time. This seemingly counterintuitive strategy incorporates an intended distribution shift to encourage alignment preservation. Fine-tuning experiments on GSM8K, ChatDoctor, and OpenOrca show that PTST significantly reduces the rise of unsafe behaviors.
Authors: Halyun Jeong, Deanna Needell, Elizaveta Rebrova
Abstract: We propose SGD-exp, a stochastic gradient descent approach for linear and ReLU regressions under Massart noise (adversarial semi-random corruption model) for the fully streaming setting. We show novel nearly linear convergence guarantees of SGD-exp to the true parameter with up to $50\%$ Massart corruption rate, and with any corruption rate in the case of symmetric oblivious corruptions. This is the first convergence guarantee result for robust ReLU regression in the streaming setting, and it shows the improved convergence rate over previous robust methods for $L_1$ linear regression due to a choice of an exponentially decaying step size, known for its efficiency in practice. Our analysis is based on the drift analysis of a discrete stochastic process, which could also be interesting on its own.
Authors: Paul Doucet, Benjamin Estermann, Till Aczel, Roger Wattenhofer
Abstract: This study addresses the integration of diversity-based and uncertainty-based sampling strategies in active learning, particularly within the context of self-supervised pre-trained models. We introduce a straightforward heuristic called TCM that mitigates the cold start problem while maintaining strong performance across various data levels. By initially applying TypiClust for diversity sampling and subsequently transitioning to uncertainty sampling with Margin, our approach effectively combines the strengths of both strategies. Our experiments demonstrate that TCM consistently outperforms existing methods across various datasets in both low and high data regimes.
Authors: Shitong Shao, Zikai Zhou, Huanran Chen, Zhiqiang Shen
Abstract: Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism. This approach significantly improves model training efficiency and is adaptable across multiple application areas. Previous methods in dataset condensation have faced challenges: some incur high computational costs which limit scalability to larger datasets (e.g., MTT, DREAM, and TESLA), while others are restricted to less optimal design spaces, which could hinder potential improvements, especially in smaller datasets (e.g., SRe2L, G-VBSM, and RDED). To address these limitations, we propose a comprehensive design framework that includes specific, effective strategies like implementing soft category-aware matching and adjusting the learning rate schedule. These strategies are grounded in empirical evidence and theoretical backing. Our resulting approach, Elucidate Dataset Condensation (EDC), establishes a benchmark for both small and large-scale dataset condensation. In our testing, EDC achieves state-of-the-art accuracy, reaching 48.6% on ImageNet-1k with a ResNet-18 model at an IPC of 10, which corresponds to a compression ratio of 0.78%. This performance exceeds those of SRe2L, G-VBSM, and RDED by margins of 27.3%, 17.2%, and 6.6%, respectively.
Authors: Rafael Oliveira, Dino Sejdinovic, David Howard, Edwin V. Bonilla
Abstract: The process of calibrating computer models of natural phenomena is essential for applications in the physical sciences, where plenty of domain knowledge can be embedded into simulations and then calibrated against real observations. Current machine learning approaches, however, mostly rely on rerunning simulations over a fixed set of designs available in the observed data, potentially neglecting informative correlations across the design space and requiring a large amount of simulations. Instead, we consider the calibration process from the perspective of Bayesian adaptive experimental design and propose a data-efficient algorithm to run maximally informative simulations within a batch-sequential process. At each round, the algorithm jointly estimates the parameters of the posterior distribution and optimal designs by maximising a variational lower bound of the expected information gain. The simulator is modelled as a sample from a Gaussian process, which allows us to correlate simulations and observed data with the unknown calibration parameters. We show the benefits of our method when compared to related approaches across synthetic and real-data problems.
Authors: Zhihui Xie, Jiahui Gao, Lei Li, Zhenguo Li, Qi Liu, Lingpeng Kong
Abstract: The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process. This misspecification occurs when the reward function fails to accurately capture the intended behavior, leading to misaligned model outputs. We introduce a metric ReGap to quantify the extent of reward misspecification and demonstrate its effectiveness and robustness in detecting harmful backdoor prompts. Building upon these insights, we present ReMiss, a system for automated red teaming that generates adversarial prompts in a reward-misspecified space. ReMiss achieves state-of-the-art attack success rates on the AdvBench benchmark against various target aligned LLMs while preserving the human readability of the generated prompts. Furthermore, these attacks on open-source models demonstrate high transferability to closed-source models like GPT-4o and out-of-distribution tasks from HarmBench. Detailed analysis highlights the unique advantages of the proposed reward misspecification objective compared to previous methods, offering new insights for improving LLM safety and robustness.
Authors: Christopher Burger, Charles Walter, Thai Le
Abstract: Recent work has investigated the vulnerability of local surrogate methods to adversarial perturbations on a machine learning (ML) model's inputs, where the explanation is manipulated while the meaning and structure of the original input remains similar under the complex model. Although weaknesses across many methods have been shown to exist, the reasons behind why remain little explored. Central to the concept of adversarial attacks on explainable AI (XAI) is the similarity measure used to calculate how one explanation differs from another. A poor choice of similarity measure can lead to erroneous conclusions on the efficacy of an XAI method. Too sensitive a measure results in exaggerated vulnerability, while too coarse understates its weakness. We investigate a variety of similarity measures designed for text-based ranked lists, including Kendall's Tau, Spearman's Footrule, and Rank-biased Overlap to determine how substantial changes in the type of measure or threshold of success affect the conclusions generated from common adversarial attack processes. Certain measures are found to be overly sensitive, resulting in erroneous estimates of stability.
Authors: Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi
Abstract: Large-scale data collections in the wild, are invariably noisy. Thus developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. In this work, we propose Geometric Median ($\gm$) Matching -- a herding style greedy algorithm that yields a $k$-subset such that the mean of the subset approximates the geometric median of the (potentially) noisy dataset. Theoretically, we show that $\gm$ Matching enjoys an improved $\gO(1/k)$ scaling over $\gO(1/\sqrt{k})$ scaling of uniform sampling; while achieving {\bf optimal breakdown point} of {\bf 1/2} even under {\bf arbitrary} corruption. Extensive experiments across several popular deep learning benchmarks indicate that $\gm$ Matching consistently improves over prior state-of-the-art; the gains become more profound at high rates of corruption and aggressive pruning rates; making $\gm$ Matching a strong baseline for future research in robust data pruning.
Authors: Han Guo, William Brandon, Radostin Cholakov, Jonathan Ragan-Kelley, Eric P. Xing, Yoon Kim
Abstract: The deployment of large language models (LLMs) is often constrained by memory bandwidth, where the primary bottleneck is the cost of transferring model parameters from the GPU's global memory to its registers. When coupled with custom kernels that fuse the dequantization and matmul operations, weight-only quantization can thus enable faster inference by reducing the amount of memory movement. However, developing high-performance kernels for weight-quantized LLMs presents substantial challenges, especially when the weights are compressed to non-evenly-divisible bit widths (e.g., 3 bits) with non-uniform, lookup table (LUT) quantization. This paper describes FLUTE, a flexible lookup table engine for LUT-quantized LLMs, which uses offline restructuring of the quantized weight matrix to minimize bit manipulations associated with unpacking, and vectorization and duplication of the lookup table to mitigate shared memory bandwidth constraints. At batch sizes < 32 and quantization group size of 128 (typical in LLM inference), the FLUTE kernel can be 2-4x faster than existing GEMM kernels. As an application of FLUTE, we explore a simple extension to lookup table-based NormalFloat quantization and apply it to quantize LLaMA3 to various configurations, obtaining competitive quantization performance against strong baselines while obtaining an end-to-end throughput increase of 1.5 to 2 times.
Authors: Enqiang Zhu, Xiang Li, Chanjuan Liu, Nikhil R. Pal
Abstract: The extraction of biomedical data has significant academic and practical value in contemporary biomedical sciences. In recent years, drug repositioning, a cost-effective strategy for drug development by discovering new indications for approved drugs, has gained increasing attention. However, many existing drug repositioning methods focus on mining information from adjacent nodes in biomedical networks without considering the potential inter-relationships between the feature spaces of drugs and diseases. This can lead to inaccurate encoding, resulting in biased mined drug-disease association information. To address this limitation, we propose a new model called Dual-Feature Drug Repurposing Neural Network (DFDRNN). DFDRNN allows the mining of two features (similarity and association) from the drug-disease biomedical networks to encode drugs and diseases. A self-attention mechanism is utilized to extract neighbor feature information. It incorporates two dual-feature extraction modules: the single-domain dual-feature extraction (SDDFE) module for extracting features within a single domain (drugs or diseases) and the cross-domain dual-feature extraction (CDDFE) module for extracting features across domains. By utilizing these modules, we ensure more appropriate encoding of drugs and diseases. A cross-dual-domain decoder is also designed to predict drug-disease associations in both domains. Our proposed DFDRNN model outperforms six state-of-the-art methods on four benchmark datasets, achieving an average AUROC of 0.946 and an average AUPR of 0.597. Case studies on two diseases show that the proposed DFDRNN model can be applied in real-world scenarios, demonstrating its significant potential in drug repositioning.
Authors: David Perera, Victor Letzelter, Th\'eo Mariotte, Adrien Cort\'es, Mickael Chen, Slim Essid, Ga\"el Richard
Abstract: We introduce Annealed Multiple Choice Learning (aMCL) which combines simulated annealing with MCL. MCL is a learning framework handling ambiguous tasks by predicting a small set of plausible hypotheses. These hypotheses are trained using the Winner-takes-all (WTA) scheme, which promotes the diversity of the predictions. However, this scheme may converge toward an arbitrarily suboptimal local minimum, due to the greedy nature of WTA. We overcome this limitation using annealing, which enhances the exploration of the hypothesis space during training. We leverage insights from statistical physics and information theory to provide a detailed description of the model training trajectory. Additionally, we validate our algorithm by extensive experiments on synthetic datasets, on the standard UCI benchmark, and on speech separation.
Authors: Jiapeng Zhu, Zichen Ding, Jianxiang Yu, Jiaqi Tan, Xiang Li, Weining Qian
Abstract: The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approaches tailored specialized prompting functions for Graph Neural Network (GNN) models pre-trained with specific strategies, such as edge prediction, thus limiting their applicability. In contrast, another pioneering line of research has explored universal prompting via adding prompts to the input graph's feature space, thereby removing the reliance on specific pre-training strategies. However, the necessity to add feature prompts to all nodes remains an open question. Motivated by findings from prompt tuning research in the NLP domain, which suggest that highly capable pre-trained models need less conditioning signal to achieve desired behaviors, we advocate for strategically incorporating necessary and lightweight feature prompts to certain graph nodes to enhance downstream task performance. This introduces a combinatorial optimization problem, requiring a policy to decide 1) which nodes to prompt and 2) what specific feature prompts to attach. We then address the problem by framing the prompt incorporation process as a sequential decision-making problem and propose our method, RELIEF, which employs Reinforcement Learning (RL) to optimize it. At each step, the RL agent selects a node (discrete action) and determines the prompt content (continuous action), aiming to maximize cumulative performance gain. Extensive experiments on graph and node-level tasks with various pre-training strategies in few-shot scenarios demonstrate that our RELIEF outperforms fine-tuning and other prompt-based approaches in classification performance and data efficiency. The code is available at https://github.com/JasonZhujp/RELIEF.
Authors: Xiaocan Li, Xiaoyu Wang, Ilia Smirnov, Scott Sanner, Baher Abdulhai
Abstract: Perimeter control (PC) prevents loss of traffic network capacity due to congestion in urban areas. Homogeneous PC allows all access points to a protected region to have identical permitted inflow. However, homogeneous PC performs poorly when the congestion in the protected region is heterogeneous (e.g., imbalanced demand) since the homogeneous PC does not consider specific traffic conditions around each perimeter intersection. When the protected region has spatially heterogeneous congestion, one needs to modulate the perimeter inflow rate to be higher near low-density regions and vice versa for high-density regions. A na\"ive approach is to leverage 1-hop traffic pressure to measure traffic condition around perimeter intersections, but such metric is too spatially myopic for PC. To address this issue, we formulate multi-hop downstream pressure grounded on Markov chain theory, which ``looks deeper'' into the protected region beyond perimeter intersections. In addition, we formulate a two-stage hierarchical control scheme that can leverage this novel multi-hop pressure to redistribute the total permitted inflow provided by a pre-trained deep reinforcement learning homogeneous control policy. Experimental results show that our heterogeneous PC approaches leveraging multi-hop pressure significantly outperform homogeneous PC in scenarios where the origin-destination flows are highly imbalanced with high spatial heterogeneity. Moveover, our approach is shown to be robust against turning ratio uncertainties by a sensitivity analysis.
Authors: Sukai Huang, Shu-Wei Liu, Nir Lipovetzky, Trevor Cohn
Abstract: While Vision-Language Models (VLMs) are increasingly used to generate reward signals for training embodied agents to follow instructions, our research reveals that agents guided by VLM rewards often underperform compared to those employing only intrinsic (exploration-driven) rewards, contradicting expectations set by recent work. We hypothesize that false positive rewards -- instances where unintended trajectories are incorrectly rewarded -- are more detrimental than false negatives. Our analysis confirms this hypothesis, revealing that the widely used cosine similarity metric is prone to false positive reward estimates. To address this, we introduce BiMI ({Bi}nary {M}utual {I}nformation), a novel reward function designed to mitigate noise. BiMI significantly enhances learning efficiency across diverse and challenging embodied navigation environments. Our findings offer a nuanced understanding of how different types of reward noise impact agent learning and highlight the importance of addressing multimodal reward signal noise when training embodied agents
Authors: Aranyak Acharyya, Michael W. Trosset, Carey E. Priebe, Hayden S. Helm
Abstract: Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different information when presented the same query. As the landscape of generative models evolves, it is important to develop techniques to study and analyze differences in model behaviour. In this paper we present novel theoretical results for embedding-based representations of generative models in the context of a set of queries. In particular, we establish sufficient conditions for the consistent estimation of the model embeddings in situations where the query set and the number of models grow.
Authors: Steve Hanneke, Kun Wang
Abstract: We study the stochastic noisy bandit problem with an unknown reward function $f^*$ in a known function class $\mathcal{F}$. Formally, a model $M$ maps arms $\pi$ to a probability distribution $M(\pi)$ of reward. A model class $\mathcal{M}$ is a collection of models. For each model $M$, define its mean reward function $f^M(\pi)=\mathbb{E}_{r \sim M(\pi)}[r]$. In the bandit learning problem, we proceed in rounds, pulling one arm $\pi$ each round and observing a reward sampled from $M(\pi)$. With knowledge of $\mathcal{M}$, supposing that the true model $M\in \mathcal{M}$, the objective is to identify an arm $\hat{\pi}$ of near-maximal mean reward $f^M(\hat{\pi})$ with high probability in a bounded number of rounds. If this is possible, then the model class is said to be learnable. Importantly, a result of \cite{hanneke2023bandit} shows there exist model classes for which learnability is undecidable. However, the model class they consider features deterministic rewards, and they raise the question of whether learnability is decidable for classes containing sufficiently noisy models. For the first time, we answer this question in the positive by giving a complete characterization of learnability for model classes with arbitrary noise. In addition to that, we also describe the full spectrum of possible optimal query complexities. Further, we prove adaptivity is sometimes necessary to achieve the optimal query complexity. Last, we revisit an important complexity measure for interactive decision making, the Decision-Estimation-Coefficient \citep{foster2021statistical,foster2023tight}, and propose a new variant of the DEC which also characterizes learnability in this setting.
Authors: Marcin Rabiza
Abstract: Despite significant advancements in XAI, scholars note a persistent lack of solid conceptual foundations and integration with broader scientific discourse on explanation. In response, emerging XAI research draws on explanatory strategies from various sciences and philosophy of science literature to fill these gaps. This paper outlines a mechanistic strategy for explaining the functional organization of deep learning systems, situating recent advancements in AI explainability within a broader philosophical context. According to the mechanistic approach, the explanation of opaque AI systems involves identifying mechanisms that drive decision-making. For deep neural networks, this means discerning functionally relevant components -- such as neurons, layers, circuits, or activation patterns -- and understanding their roles through decomposition, localization, and recomposition. Proof-of-principle case studies from image recognition and language modeling align these theoretical approaches with the latest research from AI labs like OpenAI and Anthropic. This research suggests that a systematic approach to studying model organization can reveal elements that simpler (or ''more modest'') explainability techniques might miss, fostering more thoroughly explainable AI. The paper concludes with a discussion on the epistemic relevance of the mechanistic approach positioned in the context of selected philosophical debates on XAI.
Authors: Yukun Cao, Lisheng Wang, Luobin Huang
Abstract: Temporal knowledge graph (TKG) reasoning that infers future missing facts is an essential and challenging task. Predicting future events typically relies on closely related historical facts, yielding more accurate results for repetitive or periodic events. However, for future events with sparse historical interactions, the effectiveness of this method, which focuses on leveraging high-frequency historical information, diminishes. Recently, the capabilities of diffusion models in image generation have opened new opportunities for TKG reasoning. Therefore, we propose a graph node diffusion model with dual-domain periodic contrastive learning (DPCL-Diff). Graph node diffusion model (GNDiff) introduces noise into sparsely related events to simulate new events, generating high-quality data that better conforms to the actual distribution. This generative mechanism significantly enhances the model's ability to reason about new events. Additionally, the dual-domain periodic contrastive learning (DPCL) maps periodic and non-periodic event entities to Poincar\'e and Euclidean spaces, leveraging their characteristics to distinguish similar periodic events effectively. Experimental results on four public datasets demonstrate that DPCL-Diff significantly outperforms state-of-the-art TKG models in event prediction, demonstrating our approach's effectiveness. This study also investigates the combined effectiveness of GNDiff and DPCL in TKG tasks.
Authors: Xiaocan Li, Xiaoyu Wang, Ilia Smirnov, Scott Sanner, Baher Abdulhai
Abstract: Coordination in traffic signal control is crucial for managing congestion in urban networks. Existing pressure-based control methods focus only on immediate upstream links, leading to suboptimal green time allocation and increased network delays. However, effective signal control inherently requires coordination across a broader spatial scope, as the effect of upstream traffic should influence signal control decisions at downstream intersections, impacting a large area in the traffic network. Although agent communication using neural network-based feature extraction can implicitly enhance spatial awareness, it significantly increases the learning complexity, adding an additional layer of difficulty to the challenging task of control in deep reinforcement learning. To address the issue of learning complexity and myopic traffic pressure definition, our work introduces a novel concept based on Markov chain theory, namely \textit{multi-hop upstream pressure}, which generalizes the conventional pressure to account for traffic conditions beyond the immediate upstream links. This farsighted and compact metric informs the deep reinforcement learning agent to preemptively clear the multi-hop upstream queues, guiding the agent to optimize signal timings with a broader spatial awareness. Simulations on synthetic and realistic (Toronto) scenarios demonstrate controllers utilizing multi-hop upstream pressure significantly reduce overall network delay by prioritizing traffic movements based on a broader understanding of upstream congestion.
Authors: ChangMin Ye, Yonguk Sim, Youngchae Kim, SeongMin Jin, Doo Seok Jeong
Abstract: Transformer-based large language models are a memory-bound model whose operation is based on a large amount of data that are marginally reused. Thus, the data movement between a host and accelerator likely dictates the total wall-clock time. Layer normalization is one of the key workloads in the transformer model, following each of multi-head attention and feed-forward network blocks. To reduce data movement, layer normalization needs to be performed on the same chip as the matrix-matrix multiplication engine. To this end, we introduce an iterative L2-normalization method for 1D input (IterL2Norm), ensuring fast convergence to the steady-state solution within five iteration steps and high precision, outperforming the fast inverse square root algorithm in six out of nine cases for FP32 and five out of nine for BFloat16 across the embedding lengths used in the OPT models. Implemented in 32/28nm CMOS, the IterL2Norm macro normalizes $d$-dimensional vectors, where $64 \leq d \leq 1024$, with a latency of 116-227 cycles at 100MHz/1.05V.
Authors: Nahian Ahmed, Mark Roth, Tyler A. Hallman, W. Douglas Robinson, Rebecca A. Hutchinson
Abstract: Citizen science biodiversity data present great opportunities for ecology and conservation across vast spatial and temporal scales. However, the opportunistic nature of these data lacks the sampling structure required by modeling methodologies that address a pervasive challenge in ecological data collection: imperfect detection, i.e., the likelihood of under-observing species on field surveys. Occupancy modeling is an example of an approach that accounts for imperfect detection by explicitly modeling the observation process separately from the biological process of habitat selection. This produces species distribution models that speak to the pattern of the species on a landscape after accounting for imperfect detection in the data, rather than the pattern of species observations corrupted by errors. To achieve this benefit, occupancy models require multiple surveys of a site across which the site's status (i.e., occupied or not) is assumed constant. Since citizen science data are not collected under the required repeated-visit protocol, observations may be grouped into sites post hoc. Existing approaches for constructing sites discard some observations and/or consider only geographic distance and not environmental similarity. In this study, we compare ten approaches for site construction in terms of their impact on downstream species distribution models for 31 bird species in Oregon, using observations recorded in the eBird database. We find that occupancy models built on sites constructed by spatial clustering algorithms perform better than existing alternatives.
Authors: Shihao Shao, Yikang Li, Zhouchen Lin, Qinghua Cui
Abstract: Irreducible Cartesian tensors (ICTs) play a crucial role in the design of equivariant graph neural networks, as well as in theoretical chemistry and chemical physics. Meanwhile, the design space of available linear operations on tensors that preserve symmetry presents a significant challenge. The ICT decomposition and a basis of this equivariant space are difficult to obtain for high-rank tensors. After decades of research, Bonvicini (2024) recently achieves an explicit ICT decomposition for $n=5$ with factorial time/space complexity. In this work we, for the first time, obtains decomposition matrices for ICTs up to rank $n=9$ with reduced and affordable complexity, by constructing what we call path matrices. The path matrices are obtained via performing chain-like contractions with Clebsch-Gordan matrices following the parentage scheme. We prove and leverage that the concatenation of path matrices is an orthonormal change-of-basis matrix between the Cartesian tensor product space and the spherical direct sum spaces. Furthermore, we identify a complete orthogonal basis for the equivariant space, rather than a spanning set (Pearce-Crump, 2023), through this path matrices technique. To the best of our knowledge, this is also the first analytic, rather than numerical, method for theoretically obtaining arbitrary rank orthogonal ICT decomposition matrices and orthogonal equivariant bases. We further extend our result to the arbitrary tensor product and direct sum spaces, enabling free design between different spaces while keeping symmetry. The Python code is available at https://github.com/ShihaoShao-GH/ICT-decomposition-and-equivariant-bases, where the $n=6,\dots,9$ ICT decomposition matrices are obtained in 1s, 3s, 11s, and 4m32s on 28-cores Intel(R) Xeon(R) Gold 6330 CPU @ 2.00GHz, respectively.
URLs: https://github.com/ShihaoShao-GH/ICT-decomposition-and-equivariant-bases,
Authors: Satchel Grant
Abstract: When can we say that two neural systems are the same? The answer to this question is goal-dependent, and it is often addressed through correlative methods such as Representational Similarity Analysis (RSA) and Centered Kernel Alignment (CKA). What do we miss when we forgo causal explorations, and how can we target specific types of similarity? In this work, we introduce Model Alignment Search (MAS), a method for causally exploring distributed representational similarity. The method learns invertible linear transformations that align a subspace between two distributed networks' representations where causal information can be freely interchanged. We first show that the method can be used to transfer specific causal variables, such as the number of items in a counting task, between networks with different training seeds. We then explore open questions in number cognition by comparing different types of numeric representations in models trained on structurally different numeric tasks. We then explore differences between MAS vs preexisting causal similarity methods, and lastly, we introduce a counterfactual latent auxiliary loss function that helps shape causally relevant alignments even in cases where we do not have causal access to one of the two models for training.
Authors: Zhengzhong Liu, Bowen Tan, Hongyi Wang, Willie Neiswanger, Tianhua Tao, Haonan Li, Fajri Koto, Yuqi Wang, Suqi Sun, Omkar Pangarkar, Richard Fan, Yi Gu, Victor Miller, Liqun Ma, Liping Tang, Nikhil Ranjan, Yonghao Zhuang, Guowei He, Renxi Wang, Mingkai Deng, Robin Algayres, Yuanzhi Li, Zhiqiang Shen, Preslav Nakov, Eric Xing
Abstract: We detail the training of the LLM360 K2-65B model, scaling up our 360-degree OPEN SOURCE approach to the largest and most powerful models under project LLM360. While open-source LLMs continue to advance, the answer to "How are the largest LLMs trained?" remains unclear within the community. The implementation details for such high-capacity models are often protected due to business considerations associated with their high cost. This lack of transparency prevents LLM researchers from leveraging valuable insights from prior experience, e.g., "What are the best practices for addressing loss spikes?" The LLM360 K2 project addresses this gap by providing full transparency and access to resources accumulated during the training of LLMs at the largest scale. This report highlights key elements of the K2 project, including our first model, K2 DIAMOND, a 65 billion-parameter LLM that surpasses LLaMA-65B and rivals LLaMA2-70B, while requiring fewer FLOPs and tokens. We detail the implementation steps and present a longitudinal analysis of K2 DIAMOND's capabilities throughout its training process. We also outline ongoing projects such as TXT360, setting the stage for future models in the series. By offering previously unavailable resources, the K2 project also resonates with the 360-degree OPEN SOURCE principles of transparency, reproducibility, and accessibility, which we believe are vital in the era of resource-intensive AI research.
Authors: Wennuo Yang, Shiling Wu, Yuzhi Zhou, Cheng Luo, Xilin He, Weicheng Xie, Linlin Shen, Siyang Song
Abstract: Multivariate Time Series Classification (MTSC) enables the analysis if complex temporal data, and thus serves as a cornerstone in various real-world applications, ranging from healthcare to finance. Since the relationship among variables in MTS usually contain crucial cues, a large number of graph-based MTSC approaches have been proposed, as the graph topology and edges can explicitly represent relationships among variables (channels), where not only various MTS graph representation learning strategies but also different Graph Neural Networks (GNNs) have been explored. Despite such progresses, there is no comprehensive study that fairly benchmarks and investigates the performances of existing widely-used graph representation learning strategies/GNN classifiers in the application of different MTSC tasks. In this paper, we present the first benchmark which systematically investigates the effectiveness of the widely-used three node feature definition strategies, four edge feature learning strategies and five GNN architecture, resulting in 60 different variants for graph-based MTSC. These variants are developed and evaluated with a standardized data pipeline and training/validation/testing strategy on 26 widely-used suspensor MTSC datasets. Our experiments highlight that node features significantly influence MTSC performance, while the visualization of edge features illustrates why adaptive edge learning outperforms other edge feature learning methods. The code of the proposed benchmark is publicly available at \url{https://github.com/CVI-yangwn/Benchmark-GNN-for-Multivariate-Time-Series-Classification}.
URLs: https://github.com/CVI-yangwn/Benchmark-GNN-for-Multivariate-Time-Series-Classification
Authors: Youssef Abdalla, Marrisa Taub, Eleanor Hilton, Priya Akkaraju, Alexander Milanovic, Mine Orlu, Abdul W. Basit, Michael T Cook, Tapabrata Chakraborti, David Shorthouse
Abstract: Data scarcity in pharmaceutical research has led to reliance on labour-intensive trial-and-error approaches for development rather than data-driven methods. While Machine Learning offers a solution, existing datasets are often small and noisy, limiting their utility. To address this, we developed a Variationally Encoded Conditional Tabular Generative Adversarial Network (VECT-GAN), a novel generative model specifically designed for augmenting small, noisy datasets. We introduce a pipeline where data is augmented before regression model development and demonstrate that this consistently and significantly improves performance over other state-of-the-art tabular generative models. We apply this pipeline across six pharmaceutical datasets, and highlight its real-world applicability by developing novel polymers with medically desirable mucoadhesive properties, which we made and experimentally characterised. Additionally, we pre-train the model on the ChEMBL database of drug-like molecules, leveraging knowledge distillation to enhance its generalisability, making it readily available for use on pharmaceutical datasets containing small molecules, an extremely common pharmaceutical task. We demonstrate the power of synthetic data for regularising small tabular datasets, highlighting its potential to become standard practice in pharmaceutical model development, and make our method, including VECT-GAN pre-trained on ChEMBL available as a pip package.
Authors: Yinkai Wang, Jiaxing He, Yuanqi Du, Xiaohui Chen, Jianan Canal Li, Li-Ping Liu, Xiaolin Xu, Soha Hassoun
Abstract: We consider the protein sequence engineering problem, which aims to find protein sequences with high fitness levels, starting from a given wild-type sequence. Directed evolution has been a dominating paradigm in this field which has an iterative process to generate variants and select via experimental feedback. We demonstrate large language models (LLMs), despite being trained on massive texts, are secretly protein sequence optimizers. With a directed evolutionary method, LLM can perform protein engineering through Pareto and experiment-budget constrained optimization, demonstrating success on both synthetic and experimental fitness landscapes.
Authors: Zichang Ge, Changyu Chen, Arunesh Sinha, Pradeep Varakantham
Abstract: In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering. For example, self-driving cars must replicate human driving behaviors, while robots and healthcare systems benefit from modeling decision sequences, whether or not they come from expert data. Existing trajectory encoding methods often focus on specific tasks or rely on reward signals, limiting their ability to generalize across domains and tasks. Inspired by the success of embedding models like CLIP and BERT in static domains, we propose a novel method for embedding state-action trajectories into a latent space that captures the skills and competencies in the dynamic underlying decision-making processes. This method operates without the need for reward labels, enabling better generalization across diverse domains and tasks. Our contributions are threefold: (1) We introduce a trajectory embedding approach that captures multiple abilities from state-action data. (2) The learned embeddings exhibit strong representational power across downstream tasks, including imitation, classification, clustering, and regression. (3) The embeddings demonstrate unique properties, such as controlling agent behaviors in IQ-Learn and an additive structure in the latent space. Experimental results confirm that our method outperforms traditional approaches, offering more flexible and powerful trajectory representations for various applications. Our code is available at https://github.com/Erasmo1015/vte.
Authors: Kuan-Ming Liu, Ming-Chih Lo
Abstract: Recent advances in deep learning and large language models (LLMs) have facilitated the deployment of the mixture-of-experts (MoE) mechanism in the stock investment domain. While these models have demonstrated promising trading performance, they are often unimodal, neglecting the wealth of information available in other modalities, such as textual data. Moreover, the traditional neural network-based router selection mechanism fails to consider contextual and real-world nuances, resulting in suboptimal expert selection. To address these limitations, we propose LLMoE, a novel framework that employs LLMs as the router within the MoE architecture. Specifically, we replace the conventional neural network-based router with LLMs, leveraging their extensive world knowledge and reasoning capabilities to select experts based on historical price data and stock news. This approach provides a more effective and interpretable selection mechanism. Our experiments on multimodal real-world stock datasets demonstrate that LLMoE outperforms state-of-the-art MoE models and other deep neural network approaches. Additionally, the flexible architecture of LLMoE allows for easy adaptation to various downstream tasks.
Authors: Mohammad Mahdavian, Payam Nikdel, Mahdi TaherAhmadi, Mo Chen
Abstract: In this paper, we develop a neural network model to predict future human motion from an observed human motion history. We propose a non-autoregressive transformer architecture to leverage its parallel nature for easier training and fast, accurate predictions at test time. The proposed architecture divides human motion prediction into two parts: 1) the human trajectory, which is the hip joint 3D position over time and 2) the human pose which is the all other joints 3D positions over time with respect to a fixed hip joint. We propose to make the two predictions simultaneously, as the shared representation can improve the model performance. Therefore, the model consists of two sets of encoders and decoders. First, a multi-head attention module applied to encoder outputs improves human trajectory. Second, another multi-head self-attention module applied to encoder outputs concatenated with decoder outputs facilitates learning of temporal dependencies. Our model is well-suited for robotic applications in terms of test accuracy and speed, and compares favorably with respect to state-of-the-art methods. We demonstrate the real-world applicability of our work via the Robot Follow-Ahead task, a challenging yet practical case study for our proposed model.
Authors: Lei Xin, Lintao Ye, George Chiu, Shreyas Sundaram
Abstract: We consider the problem of learning the dynamics of a linear system when one has access to data generated by an auxiliary system that shares similar (but not identical) dynamics, in addition to data from the true system. We use a weighted least squares approach, and provide finite sample error bounds of the learned model as a function of the number of samples and various system parameters from the two systems as well as the weight assigned to the auxiliary data. We show that the auxiliary data can help to reduce the intrinsic system identification error due to noise, at the price of adding a portion of error that is due to the differences between the two system models. We further provide a data-dependent bound that is computable when some prior knowledge about the systems, such as upper bounds on noise levels and model difference, is available. This bound can also be used to determine the weight that should be assigned to the auxiliary data during the model training stage.
Authors: Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi
Abstract: Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use. Consequently, the reliable detection of AI-generated text has become a critical area of research. AI text detectors have shown to be effective under their specific settings. In this paper, we stress-test the robustness of these AI text detectors in the presence of an attacker. We introduce recursive paraphrasing attack to stress test a wide range of detection schemes, including the ones using the watermarking as well as neural network-based detectors, zero shot classifiers, and retrieval-based detectors. Our experiments conducted on passages, each approximately 300 tokens long, reveal the varying sensitivities of these detectors to our attacks. Our findings indicate that while our recursive paraphrasing method can significantly reduce detection rates, it only slightly degrades text quality in many cases, highlighting potential vulnerabilities in current detection systems in the presence of an attacker. Additionally, we investigate the susceptibility of watermarked LLMs to spoofing attacks aimed at misclassifying human-written text as AI-generated. We demonstrate that an attacker can infer hidden AI text signatures without white-box access to the detection method, potentially leading to reputational risks for LLM developers. Finally, we provide a theoretical framework connecting the AUROC of the best possible detector to the Total Variation distance between human and AI text distributions. This analysis offers insights into the fundamental challenges of reliable detection as language models continue to advance. Our code is publicly available at https://github.com/vinusankars/Reliability-of-AI-text-detectors.
URLs: https://github.com/vinusankars/Reliability-of-AI-text-detectors.
Authors: Philipp Kuehn, Dilara Nadermahmoodi, Markus Bayer, Christian Reuter
Abstract: Public information contains valuable Cyber Threat Intelligence (CTI) that is used to prevent attacks in the future. Ideally, the learnings from previous attacks help to mitigate all those that follow. While there are standards for sharing this information, much of it is shared in non-standardized news articles or blog posts. It is a time-consuming task to monitor online sources for threats and even then, one can never be sure, to use the right sources. Current research propose extractors of Indicators of Compromise from known sources, while the identification of new sources is rarely considered. This paper proposes a focused crawler focused on the CTI domain based on multi-armed bandit ( MAB) and different crawling strategies. It uses SBERT to identify relevant documents, while dynamically adapt its crawling path. We propose a system called ThreatCrawl, which achieve a harvest rate of over 25% and is able to expand its used seed by over 300%, while retaining focus on the topic at hand. In addition, this crawler identified previously unknown but highly relevant overview pages, datasets, and domains.
Authors: Jiayang Shi, Daniel M. Pelt, K. Joost Batenburg
Abstract: Computed Tomography (CT) using synchrotron radiation is a powerful technique that, compared to lab-CT techniques, boosts high spatial and temporal resolution while also providing access to a range of contrast-formation mechanisms. The acquired projection data is typically processed by a computational pipeline composed of multiple stages. Artifacts introduced during data acquisition can propagate through the pipeline, and degrade image quality in the reconstructed images. Recently, deep learning has shown significant promise in enhancing image quality for images representing scientific data. This success has driven increasing adoption of deep learning techniques in CT imaging. Various approaches have been proposed to incorporate deep learning into computational pipelines, but each has limitations in addressing artifacts effectively and efficiently in synchrotron CT, either in properly addressing the specific artifacts, or in computational efficiency. Recognizing these challenges, we introduce a novel method that incorporates separate deep learning models at each stage of the tomography pipeline-projection, sinogram, and reconstruction-to address specific artifacts locally in a data-driven way. Our approach includes bypass connections that feed both the outputs from previous stages and raw data to subsequent stages, minimizing the risk of error propagation. Extensive evaluations on both simulated and real-world datasets illustrate that our approach effectively reduces artifacts and outperforms comparison methods.
Authors: Viveck R. Cadambe, Ateet Devulapalli, Haewon Jeong, Flavio P. Calmon
Abstract: We consider the problem of private distributed multi-party multiplication. It is well-established that Shamir secret-sharing coding strategies can enable perfect information-theoretic privacy in distributed computation via the celebrated algorithm of Ben Or, Goldwasser and Wigderson (the "BGW algorithm"). However, perfect privacy and accuracy require an honest majority, that is, $N \geq 2t+1$ compute nodes are required to ensure privacy against any $t$ colluding adversarial nodes. By allowing for some controlled amount of information leakage and approximate multiplication instead of exact multiplication, we study coding schemes for the setting where the number of honest nodes can be a minority, that is $N< 2t+1.$ We develop a tight characterization privacy-accuracy trade-off for cases where $N < 2t+1$ by measuring information leakage using {differential} privacy instead of perfect privacy, and using the mean squared error metric for accuracy. A novel technical aspect is an intricately layered noise distribution that merges ideas from differential privacy and Shamir secret-sharing at different layers.
Authors: Atoosa Kasirzadeh
Abstract: The conventional discourse on existential risks (x-risks) from AI typically focuses on abrupt, dire events caused by advanced AI systems, particularly those that might achieve or surpass human-level intelligence. These events have severe consequences that either lead to human extinction or irreversibly cripple human civilization to a point beyond recovery. This discourse, however, often neglects the serious possibility of AI x-risks manifesting incrementally through a series of smaller yet interconnected disruptions, gradually crossing critical thresholds over time. This paper contrasts the conventional "decisive AI x-risk hypothesis" with an "accumulative AI x-risk hypothesis." While the former envisions an overt AI takeover pathway, characterized by scenarios like uncontrollable superintelligence, the latter suggests a different causal pathway to existential catastrophes. This involves a gradual accumulation of critical AI-induced threats such as severe vulnerabilities and systemic erosion of economic and political structures. The accumulative hypothesis suggests a boiling frog scenario where incremental AI risks slowly converge, undermining societal resilience until a triggering event results in irreversible collapse. Through systems analysis, this paper examines the distinct assumptions differentiating these two hypotheses. It is then argued that the accumulative view can reconcile seemingly incompatible perspectives on AI risks. The implications of differentiating between these causal pathways -- the decisive and the accumulative -- for the governance of AI as well as long-term AI safety are discussed.
Authors: Nayoung Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
Abstract: Recently, deep learning has made rapid progress in antibody design, which plays a key role in the advancement of therapeutics. A dominant paradigm is to train a model to jointly generate the antibody sequence and the structure as a candidate. However, the joint generation requires the model to generate both the discrete amino acid categories and the continuous 3D coordinates; this limits the space of possible architectures and may lead to suboptimal performance. In response, we propose an antibody sequence-structure decoupling (ASSD) framework, which separates sequence generation and structure prediction. Although our approach is simple, our idea allows the use of powerful neural architectures and demonstrates notable performance improvements. We also find that the widely used non-autoregressive generators promote sequences with overly repeating tokens. Such sequences are both out-of-distribution and prone to undesirable developability properties that can trigger harmful immune responses in patients. To resolve this, we introduce a composition-based objective that allows an efficient trade-off between high performance and low token repetition. ASSD shows improved performance in various antibody design experiments, while the composition-based objective successfully mitigates token repetition of non-autoregressive models.
Authors: Matteo Cederle, Luca Vittorio Piron, Marina Ceccon, Federico Chiariotti, Alessandro Fabris, Marco Fabris, Gian Antonio Susto
Abstract: As Machine Learning grows in popularity across various fields, equity has become a key focus for the AI community. However, fairness-oriented approaches are still underexplored in smart mobility. Addressing this gap, our study investigates the balance between performance optimization and algorithmic fairness in shared micromobility services providing a novel framework based on Reinforcement Learning. Exploiting Q-learning, the proposed methodology achieves equitable outcomes in terms of the Gini index across different areas characterized by their distance from central hubs. Through vehicle rebalancing, the provided scheme maximizes operator performance while ensuring fairness principles for users, reducing iniquity by up to 85% while only increasing costs by 30% (w.r.t. applying no equity adjustment). A case study with synthetic data validates our insights and highlights the importance of fairness in urban micromobility (source code: https://github.com/mcederle99/FairMSS.git).
Authors: Yinhong Liu, Han Zhou, Zhijiang Guo, Ehsan Shareghi, Ivan Vuli\'c, Anna Korhonen, Nigel Collier
Abstract: Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations that align with human assessments. In this work, we first conduct a systematic study of the misalignment between LLM evaluators and human evaluation, revealing that existing calibration methods aimed at mitigating biases of LLMs are insufficient for effectively aligning LLM evaluators. Inspired by the use of preference data in RLHF, we formulate the evaluation as a ranking problem and introduce Pairwise-preference Search (PAIRS), an uncertainty-guided search-based rank aggregation method that employs LLMs to conduct pairwise comparisons locally and efficiently ranks candidate texts globally. PAIRS achieves state-of-the-art performance on representative evaluation tasks in long-form generations and demonstrates significant improvements over direct scoring. Furthermore, we provide insights into the role of pairwise preference in quantifying the transitivity of LLMs and demonstrate how PAIRS benefits from calibration using debiased pairwise evaluations.
Authors: Thibaut Thonet, Jos Rozen, Laurent Besacier
Abstract: Research on Large Language Models (LLMs) has recently witnessed an increasing interest in extending the models' context size to better capture dependencies within long documents. While benchmarks have been proposed to assess long-range abilities, existing efforts primarily considered generic tasks that are not necessarily aligned with real-world applications. In contrast, we propose a new benchmark for long-context LLMs focused on a practical meeting assistant scenario in which the long contexts consist of transcripts obtained by automatic speech recognition, presenting unique challenges for LLMs due to the inherent noisiness and oral nature of such data. Our benchmark, ELITR-Bench, augments the existing ELITR corpus by adding 271 manually crafted questions with their ground-truth answers, as well as noisy versions of meeting transcripts altered to target different Word Error Rate levels. Our experiments with 12 long-context LLMs on ELITR-Bench confirm the progress made across successive generations of both proprietary and open models, and point out their discrepancies in terms of robustness to transcript noise. We also provide a thorough analysis of our GPT-4-based evaluation, including insights from a crowdsourcing study. Our findings indicate that while GPT-4's scores align with human judges, its ability to distinguish beyond three score levels may be limited.
Authors: Elodie Germani (EMPENN, LACODAM), Camille Maumet (EMPENN), Elisa Fromont (LACODAM)
Abstract: We propose a novel approach to improve the reproducibility of neuroimaging results by converting statistic maps across different functional MRI pipelines. We make the assumption that pipelines used to compute fMRI statistic maps can be considered as a style component and we propose to use different generative models, among which, Generative Adversarial Networks (GAN) and Diffusion Models (DM) to convert statistic maps across different pipelines. We explore the performance of multiple GAN frameworks, and design a new DM framework for unsupervised multi-domain styletransfer. We constrain the generation of 3D fMRI statistic maps using the latent space of an auxiliary classifier that distinguishes statistic maps from different pipelines and extend traditional sampling techniques used in DM to improve the transition performance. Our experiments demonstrate that our proposed methods aresuccessful: pipelines can indeed be transferred as a style component, providing animportant source of data augmentation for future medical studies.
Authors: G. Ibikunle, B. Moews, D. Muravyev, K. Rzayev
Abstract: We design and train machine learning models to capture the nonlinear interactions between financial market dynamics and high-frequency trading (HFT) activity. In doing so, we introduce new metrics to identify liquidity-demanding and -supplying HFT strategies. Both types of HFT strategies increase activity in response to information events and decrease it when trading speed is restricted, with liquidity-supplying strategies demonstrating greater responsiveness. Liquidity-demanding HFT is positively linked with latency arbitrage opportunities, whereas liquidity-supplying HFT is negatively related, aligning with theoretical expectations. Our metrics have implications for understanding the information production process in financial markets.
Authors: Peng Liu, Nian Wang, Cong Xu, Ming Zhao, Bin Wang, Yi Ren
Abstract: Recommender Systems (RSs) provide personalized recommendation service based on user interest, which are widely used in various platforms. However, there are lots of users with sparse interest due to lacking consumption behaviors, which leads to poor recommendation results for them. This problem is widespread in large-scale RSs and is particularly difficult to address. To solve this problem, we propose a novel solution named User Interest Enhancement (UIE) which enhances user interest including user profile and user history behavior sequences using the enhancement vectors and personalized enhancement vector generated based on stream clustering and memory networks from different perspectives. UIE not only remarkably improves model performance on the users with sparse interest but also significantly enhance model performance on other users. UIE is an end-to-end solution which is easy to be implemented based on ranking model. Moreover, we expand our solution and apply similar methods to long-tail items, which also achieves excellent improvement. Furthermore, we conduct extensive offline and online experiments in a large-scale industrial RS. The results demonstrate that our model outperforms other models remarkably, especially for the users with sparse interest. Until now, UIE has been fully deployed in multiple large-scale RSs and achieved remarkable improvements.
Authors: Carlos Sebasti\'an, Carlos E. Gonz\'alez-Guill\'en, Jes\'us Juan
Abstract: Constructing prediction intervals for time series forecasting is challenging, particularly when practitioners rely solely on point forecasts. While previous research has focused on creating increasingly efficient intervals, we argue that standard measures alone are inadequate. Beyond efficiency, prediction intervals must adapt their width based on the difficulty of the prediction while preserving coverage regardless of complexity. To address these issues, we propose combining Heteroscedastic Quantile Regression (HQR) with Width-Adaptive Conformal Inference (WACI). This integrated procedure guarantees theoretical coverage and enables interval widths to vary with predictive uncertainty. We assess its performance using both a synthetic example and a real world Electricity Price Forecasting scenario. Our results show that this combined approach meets or surpasses typical benchmarks for validity and efficiency, while also fulfilling important yet often overlooked practical requirements.
Authors: Benjamin C\^ot\'e, H\'el\`ene Cossette, Etienne Marceau
Abstract: A new family of tree-structured Markov random fields for a vector of discrete counting random variables is introduced. According to the characteristics of the family, the marginal distributions of the Markov random fields are all Poisson with the same mean, and are untied from the strength or structure of their built-in dependence. This key feature is uncommon for Markov random fields and most convenient for applications purposes. The specific properties of this new family confer a straightforward sampling procedure and analytic expressions for the joint probability mass function and the joint probability generating function of the vector of counting random variables, thus granting computational methods that scale well to vectors of high dimension. We study the distribution of the sum of random variables constituting a Markov random field from the proposed family, analyze a random variable's individual contribution to that sum through expected allocations, and establish stochastic orderings to assess a wide understanding of their behavior.
Authors: Jiaxing Wu, Lin Ning, Luyang Liu, Harrison Lee, Neo Wu, Chao Wang, Sushant Prakash, Shawn O'Banion, Bradley Green, Jun Xie
Abstract: LLM-powered personalization agent systems employ Large Language Models (LLMs) to predict users' behavior from their past activities. However, their effectiveness often hinges on the ability to effectively leverage extensive, long user historical data due to its inherent noise and length of such data. Existing pretrained LLMs may generate summaries that are concise but lack the necessary context for downstream tasks, hindering their utility in personalization systems. To address these challenges, we introduce Reinforcement Learning from Prediction Feedback (RLPF). RLPF fine-tunes LLMs to generate concise, human-readable user summaries that are optimized for downstream task performance. By maximizing the usefulness of the generated summaries, RLPF effectively distills extensive user history data while preserving essential information for downstream tasks. Our empirical evaluation demonstrates significant improvements in both extrinsic downstream task utility and intrinsic summary quality, surpassing baseline methods by up to 22% on downstream task performance and achieving an up to 84.59% win rate on Factuality, Abstractiveness, and Readability. RLPF also achieves a remarkable 74% reduction in context length while improving performance on 16 out of 19 unseen tasks and/or datasets, showcasing its generalizability. This approach offers a promising solution for enhancing LLM personalization by effectively transforming long, noisy user histories into informative and human-readable representations.
Authors: Teresa Dorszewski, Albert Kj{\o}ller Jacobsen, Lenka T\v{e}tkov\'a, Lars Kai Hansen
Abstract: Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection. Recent studies on transformer models revealed a high redundancy between layers and the potential for significant pruning, which we will investigate here for transformer-based speech representation models. We perform a detailed analysis of layer similarity in speech representation models using three similarity metrics: cosine similarity, centered kernel alignment, and mutual nearest-neighbor alignment. Our findings reveal a block-like structure of high similarity, suggesting two main processing steps and significant redundancy of layers. We demonstrate the effectiveness of pruning transformer-based speech representation models without the need for post-training, achieving up to 40% reduction in transformer layers while maintaining over 95% of the model's predictive capacity. Furthermore, we employ a knowledge distillation method to substitute the entire transformer stack with mimicking layers, reducing the network size 95-98% and the inference time by up to 94%. This substantial decrease in computational load occurs without considerable performance loss, suggesting that the transformer stack is almost completely redundant for downstream applications of speech representation models.
Authors: Or Ordentlich, Yury Polyanskiy
Abstract: Recent work in machine learning community proposed multiple methods for performing lossy compression (quantization) of large matrices. This quantization is important for accelerating matrix multiplication (main component of large language models), which is often bottlenecked by the speed of loading these matrices from memory. Unlike classical vector quantization and rate-distortion theory, the goal of these new compression algorithms is to be able to approximate not the matrices themselves, but their matrix product. Specifically, given a pair of real matrices $A,B$ an encoder (compressor) is applied to each of them independently producing descriptions with $R$ bits per entry. These representations subsequently are used by the decoder to estimate matrix product $A^\top B$. In this work, we provide a non-asymptotic lower bound on the mean squared error of this approximation (as a function of rate $R$) for the case of matrices $A,B$ with iid Gaussian entries. Algorithmically, we construct a universal quantizer based on nested lattices with an explicit guarantee of approximation error for any (non-random) pair of matrices $A$, $B$ in terms of only Frobenius norms $\|\bar{A}\|_F, \|\bar{B}\|_F$ and $\|\bar{A}^\top \bar{B}\|_F$, where $\bar{A},\bar{B}$ are versions of $A,B$ with zero-centered columns, respectively. For iid Gaussian matrices our quantizer achieves the lower bound and is, thus, asymptotically optimal. A practical low-complexity version of our quantizer achieves performance quite close to optimal. In addition, we derive rate-distortion function for matrix multiplication of iid Gaussian matrices, which exhibits an interesting phase-transition at $R\approx 0.906$ bit/entry.
Authors: Xingya Wang, Yang Han, Yushi Liu, Szu-Yu Tang, Jason C. Hsu
Abstract: The ideal estimand for comparing treatment $Rx$ with a control $C$ is the $\textit{counterfactual}$ efficacy $Rx:C$, the expected differential outcome between $Rx$ and $C$ if each patient were given $\textit{both}$. One hundred years ago, Neyman (1923a) proved unbiased $\textit{point estimation}$ of counterfactual efficacy from designed $\textit{factual}$ experiments is achievable. But he left the determination of how much might the counterfactual variance of this estimate be smaller than the factual variance as an open challenge. This article shows $\textit{counterfactual}$ uncertainty quantification (CUQ), quantifying uncertainty for factual point estimates but in a counterfactual setting, is achievable for Randomized Controlled Trials (RCTs) with Before-and-After treatment Repeated Measures which are common in many therapeutic areas. We achieve CUQ whose variability is typically smaller than factual UQ by creating a new statistical modeling principle called ETZ. We urge caution in using predictors with measurement error which violates standard regression assumption and can cause $\textit{attenuation}$ in estimating treatment effects. Fortunately, we prove that, for traditional medicine in general, and for targeted therapy with efficacy defined as averaged over the population, counterfactual point estimation is unbiased. However, for both Real Human and Digital Twins approaches, predicting treatment effect in $\textit{subgroups}$ may have attenuation bias.
Authors: Yandong Li, Francesco Monticone
Abstract: Similar to algorithms, which consume time and memory to run, hardware requires resources to function. For devices processing physical waves, implementing operations needs sufficient "space," as dictated by wave physics. How much space is needed to perform a certain function is a fundamental question in optics, with recent research addressing it for given mathematical operations, but not for more general computing tasks, e.g., classification. Inspired by computational complexity theory, we study the "spatial complexity" of optical computing systems in terms of scaling laws - specifically, how their physical dimensions must scale as the dimension of the mathematical operation increases - and propose a new paradigm for designing optical computing systems: space-efficient neuromorphic optics, based on structural sparsity constraints and neural pruning methods motivated by wave physics (notably, the concept of "overlapping nonlocality"). On two mainstream platforms, free-space optics and on-chip integrated photonics, our methods demonstrate substantial size reductions (to 1%-10% the size of conventional designs) with minimal compromise on performance. Our theoretical and computational results reveal a trend of diminishing returns on accuracy as structure dimensions increase, providing a new perspective for interpreting and approaching the ultimate limits of optical computing - a balanced trade-off between device size and accuracy.
Authors: Larry Schester, Luis E. Ortiz
Abstract: Vehicles today can drive themselves on highways and driverless robotaxis operate in major cities, with more sophisticated levels of autonomous driving expected to be available and become more common in the future. Yet, technically speaking, so-called "Level 5" (L5) operation, corresponding to full autonomy, has not been achieved. For that to happen, functions such as fully autonomous highway ramp entry must be available, and provide provably safe, and reliably robust behavior to enable full autonomy. We present a systematic study of a highway ramp function that controls the vehicles forward-moving actions to minimize collisions with the stream of highway traffic into which a merging (ego) vehicle enters. We take a game-theoretic multi-agent (MA) approach to this problem and study the use of controllers based on deep reinforcement learning (DRL). The virtual environment of the MA DRL uses self-play with simulated data where merging vehicles safely learn to control longitudinal position during a taper-type merge. The work presented in this paper extends existing work by studying the interaction of more than two vehicles (agents) and does so by systematically expanding the road scene with additional traffic and ego vehicles. While previous work on the two-vehicle setting established that collision-free controllers are theoretically impossible in fully decentralized, non-coordinated environments, we empirically show that controllers learned using our approach are nearly ideal when measured against idealized optimal controllers.
Authors: Cagatay Isil, Figen S. Oktem
Abstract: In the phase retrieval problem, the aim is the recovery of an unknown image from intensity-only measurements such as Fourier intensity. Although there are several solution approaches, solving this problem is challenging due to its nonlinear and ill-posed nature. Recently, learning-based approaches have emerged as powerful alternatives to the analytical methods for several inverse problems. In the context of phase retrieval, a novel plug-and-play approach that exploits learning-based prior and efficient update steps has been presented at the Computational Optical Sensing and Imaging topical meeting, with demonstrated state-of-the-art performance. The key idea was to incorporate learning-based prior to the Gerchberg-Saxton type algorithms through plug-and-play regularization. In this paper, we present the mathematical development of the method including the derivation of its analytical update steps based on half-quadratic splitting and comparatively evaluate its performance through extensive simulations on a large test dataset. The results show the effectiveness of the method in terms of both image quality, computational efficiency, and robustness to initialization and noise.
Authors: Apurv Shukla, Debabrota Basu
Abstract: We study the preference-based pure exploration problem for bandits with vector-valued rewards. The rewards are ordered using a (given) preference cone $\mathcal{C}$ and our goal is to identify the set of Pareto optimal arms. First, to quantify the impact of preferences, we derive a novel lower bound on sample complexity for identifying the most preferred policy with a confidence level $1-\delta$. Our lower bound elicits the role played by the geometry of the preference cone and punctuates the difference in hardness compared to existing best-arm identification variants of the problem. We further explicate this geometry when the rewards follow Gaussian distributions. We then provide a convex relaxation of the lower bound and leverage it to design the Preference-based Track and Stop (PreTS) algorithm that identifies the most preferred policy. Finally, we show that the sample complexity of PreTS is asymptotically tight by deriving a new concentration inequality for vector-valued rewards.
Authors: Zhen Zheng, Xin Ji, Taosong Fang, Fanghao Zhou, Chuanjie Liu, Gang Peng
Abstract: Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks. Many of these tasks are performed in large batches or even offline, and the performance indictor for which is throughput. These tasks usually show the characteristic of prefix sharing, where different prompt input can partially show the common prefix. However, the existing LLM inference engines tend to optimize the streaming requests and show limitations of supporting the large batched tasks with the prefix sharing characteristic. The existing solutions use the LRU-based cache to reuse the KV context of common prefix between requests. The KV context that are about to be reused may prematurely evicted with the implicit cache management. Besides, the streaming oriented systems do not leverage the request-batch information and can not mix the decoding tokens with the prefill chunks to the best for the batched scenarios, and thus fails to saturate the GPU. We propose BatchLLM to address the above problems. BatchLLM explicitly identifies the common prefixes globally. The requests sharing the same prefix will be scheduled together to reuse the KV context the best. BatchLLM reorders the requests and schedules the requests with larger ratio of decoding first to better mix the decoding tokens with the latter prefill chunks, and applies memory-centric token batching to enlarge the token-batch sizes, which helps to increase the GPU utilization. Finally, BatchLLM optimizes the prefix-shared Attention kernel with horizontal fusion to reduce tail effect and kernel launch overhead. Extensive evaluation shows that BatchLLM outperforms vLLM and SGLang by 1.3$\times$ to 10.8$\times$ on a set of microbenchmarks and a typical industry workload under different hardware environments.
Authors: Irham T. Andika, Stefan Schuldt, Sherry H. Suyu, Satadru Bag, Raoul Ca\~nameras, Alejandra Melo, Claudio Grillo, James H. H. Chan
Abstract: Strongly lensed quasars provide valuable insights into the rate of cosmic expansion, the distribution of dark matter in foreground deflectors, and the characteristics of quasar hosts. However, detecting them in astronomical images is difficult due to the prevalence of non-lensing objects. To address this challenge, we developed a generative deep learning model called VariLens, built upon a physics-informed variational autoencoder. This model seamlessly integrates three essential modules: image reconstruction, object classification, and lens modeling, offering a fast and comprehensive approach to strong lens analysis. VariLens is capable of rapidly determining both (1) the probability that an object is a lens system and (2) key parameters of a singular isothermal ellipsoid (SIE) mass model -- including the Einstein radius ($\theta_\mathrm{E}$), lens center, and ellipticity -- in just milliseconds using a single CPU. A direct comparison of VariLens estimates with traditional lens modeling for 20 known lensed quasars within the Subaru Hyper Suprime-Cam (HSC) footprint shows good agreement, with both results consistent within $2\sigma$ for systems with $\theta_\mathrm{E}<3$ arcsecs. To identify new lensed quasar candidates, we begin with an initial sample of approximately 80 million sources, combining HSC data with multiwavelength information from various surveys. After applying a photometric preselection aimed at locating $z>1.5$ sources, the number of candidates is reduced to 710,966. Subsequently, VariLens highlights 13,831 sources, each showing a high likelihood of being a lens. A visual assessment of these objects results in 42 promising candidates that await spectroscopic confirmation. These results underscore the potential of automated deep learning pipelines to efficiently detect and model strong lenses in large datasets.
Authors: Zihan Liu, Yang Chen, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Abstract: In this paper, we introduce AceMath, a suite of frontier math models that excel in solving complex math problems, along with highly effective reward models capable of evaluating generated solutions and reliably identifying the correct ones. To develop the instruction-tuned math models, we propose a supervised fine-tuning (SFT) process that first achieves competitive performance across general domains, followed by targeted fine-tuning for the math domain using a carefully curated set of prompts and synthetically generated responses. The resulting model, AceMath-72B-Instruct greatly outperforms Qwen2.5-Math-72B-Instruct, GPT-4o and Claude-3.5 Sonnet. To develop math-specialized reward model, we first construct AceMath-RewardBench, a comprehensive and robust benchmark for evaluating math reward models across diverse problems and difficulty levels. After that, we present a systematic approach to build our math reward models. The resulting model, AceMath-72B-RM, consistently outperforms state-of-the-art reward models. Furthermore, when combining AceMath-72B-Instruct with AceMath-72B-RM, we achieve the highest average rm@8 score across the math reasoning benchmarks. We release model weights, training data, and evaluation benchmarks at: https://research.nvidia.com/labs/adlr/acemath
Authors: Xu Li, Yi Zheng, Haotian Chen, Xiaolei Chen, Yuxuan Liang, Chenghang Lai, Bin Li, Xiangyang Xue
Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. However, current LVLMs primarily rely on visual features extracted from the final layers of the vision encoder, overlooking the complementary information available in shallower layers. While recent approaches have explored the use of multilayer visual features in LVLMs, they tend to be task-agnostic and fail to examine the dependencies of hierarchical visual features on specific tasks. To address these gaps, we systematically investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories. Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance. Building on these insights, we propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions, without increasing the number of visual tokens. Extensive evaluations demonstrate the superior performance of our method. Additionally, an in-depth analysis of the aggregator's behavior highlights the dominance of mid-to-high-level features in semantic-rich tasks and the critical role of low-level features in fine-grained perception.