Learning Theory

Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg ICML 2025 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NeurIPS 2024 f-Divergence Based Classification: Beyond the Use of Cross-Entropy ICML 2024 H-Consistency Guarantees for Regression ICML 2024 Õ(T^-1) Convergence to (coarse) correlated equilibria in full-information general-sum Markov games L4DC 2024 2D-OOB: Attributing Data Contribution Through Joint Valuation Framework NeurIPS 2024 4+3 Phases of Compute-Optimal Neural Scaling Laws NeurIPS 2024 Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses AISTATS 2024 Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence ICML 2024 A Canonicalization Perspective on Invariant and Equivariant Learning NeurIPS 2024 A Careful Examination of Large Language Model Performance on Grade School Arithmetic NeurIPS 2024 Accelerating ERM for data-driven algorithm design using output-sensitive techniques NeurIPS 2024 Accelerating Matroid Optimization through Fast Imprecise Oracles NeurIPS 2024 A Characterization of Multioutput Learnability JMLR 2024 A Characterization Theorem for Equivariant Networks with Point-wise Activations ICLR 2024 Achievable distributional robustness when the robust risk is only partially identified NeurIPS 2024 Achieving Õ(1/ε) Sample Complexity for Constrained Markov Decision Process NeurIPS 2024 Achieving Constant Regret in Linear Markov Decision Processes NeurIPS 2024 Achieving Tractable Minimax Optimal Regret in Average Reward MDPs NeurIPS 2024 Achilles-Bench: A Challenging Benchmark for Low-Resource Evaluation ACL 2024 A Closer Look at Curriculum Adversarial Training: From an Online Perspective AAAI 2024 A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression NeurIPS 2024 A Comprehensive Evaluation of Inductive Reasoning Capabilities and Problem Solving in Large Language Models EACL 2024 A Cross-Domain Benchmark for Active Learning NeurIPS 2024 Active Classification with Few Queries under Misspecification NeurIPS 2024