Learning Theory

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes CVPR 2024 The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis EMNLP 2024 The Mystery of the Pathological Path-star Task for Language Models EMNLP 2024 Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability ICML 2024 Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach ICLR 2024 Theoretical Analysis of Weak-to-Strong Generalization NeurIPS 2024 Theoretical and Empirical Analysis of Cost-Function Merging for Implicit Hitting Set WCSP Solving AAAI 2024 Theoretical Understanding of Learning from Adversarial Perturbations ICLR 2024 The Power of Extrapolation in Federated Learning NeurIPS 2024 The Power of Resets in Online Reinforcement Learning NeurIPS 2024 The Price of Implicit Bias in Adversarially Robust Generalization NeurIPS 2024 The Privacy Power of Correlated Noise in Decentralized Learning ICML 2024 The Real Price of Bandit Information in Multiclass Classification COLT 2024 The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A” ICLR 2024 The Role of Learning Algorithms in Collective Action ICML 2024 The Role of Over-Parameterization in Machine Learning – the Good, the Bad, the Ugly AAAI 2024 The sample complexity of ERMs in stochastic convex optimization AISTATS 2024 The Sample Complexity of Gradient Descent in Stochastic Convex Optimization NeurIPS 2024 The sample complexity of multi-distribution learning COLT 2024 The Semantic Relations in LLMs: An Information-theoretic Compression Approach COLING 2024 The SMART approach to instance-optimal online learning COLT 2024 The Star Number and Eluder Dimension: Elementary Observations About the Dimensions of Disagreement COLT 2024 The surprising efficiency of temporal difference learning for rare event prediction NeurIPS 2024 Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance JMLR 2024 Tight Bounds for Learning RUMs from Small Slates NeurIPS 2024