Theory

Approximating the Top Eigenvector in Random Order Streams NeurIPS 2024 A Precise Characterization of SGD Stability Using Loss Surface Geometry ICLR 2024 A Proposal for Scaling the Scaling Laws EACL 2024 A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness NeurIPS 2024 A Rainbow in Deep Network Black Boxes JMLR 2024 A Recipe for Improved Certifiable Robustness ICLR 2024 Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? NeurIPS 2024 Are Large Language Models (LLMs) Good Social Predictors? EMNLP 2024 Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data ACL 2024 A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base NAACL 2024 Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators? ICLR 2024 A Simple and Optimal Approach for Universal Online Learning with Gradient Variations NeurIPS 2024 Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability NeurIPS 2024 A Study on the Calibration of In-context Learning NAACL 2024 A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) AAAI 2024 A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers NAACL 2024 A Tale of Two Revisions: Summarizing Changes Across Document Versions ACL 2024 A Theoretical Perspective for Speculative Decoding Algorithm NeurIPS 2024 A Theory of Joint Light and Heat Transport for Lambertian Scenes CVPR 2024 A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks ICML 2024 A Theory of Optimistically Universal Online Learnability for General Concept Classes NeurIPS 2024 A Top-Down Tree Model Counter for Quantified Boolean Formulas IJCAI 2024 A Topological Perspective on Demystifying GNN-Based Link Prediction Performance ICLR 2024 Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models ICLR 2024 AudioMarkBench: Benchmarking Robustness of Audio Watermarking NeurIPS 2024