Learning Theory

Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference NeurIPS 2023 Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network ICML 2023 Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies ICML 2023 Strategic Classification under Unknown Personalized Manipulation NeurIPS 2023 Strong inductive biases provably prevent harmless interpolation ICLR 2023 Strong Lottery Ticket Hypothesis with ε–perturbation AISTATS 2023 Structured Prediction with Stronger Consistency Guarantees NeurIPS 2023 Supervision Complexity and its Role in Knowledge Distillation ICLR 2023 Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration NeurIPS 2023 Systematic Generalization by Finetuning? Analyzing Pretrained Language Models Using Constituency Tests EMNLP 2023 System Identification of Neural Systems: If We Got It Right, Would We Know? ICML 2023 Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds NeurIPS 2023 TaskWeb: Selecting Better Source Tasks for Multi-task NLP EMNLP 2023 Taylor TD-learning NeurIPS 2023 Tester-Learners for Halfspaces: Universal Algorithms NeurIPS 2023 Testing of Horn Samplers AISTATS 2023 Testing of Index-Invariant Properties in the Huge Object Model COLT 2023 Testing Tail Weight of a Distribution Via Hazard Rate ALT 2023 TextVerifier: Robustness Verification for Textual Classifiers with Certifiable Guarantees ACL 2023 The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization AAAI 2023 The Art of BART: Minimax Optimality over Nonhomogeneous Smoothness in High Dimension JMLR 2023 The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks ICLR 2023 The Bayesian Stability Zoo NeurIPS 2023 The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning NeurIPS 2023 The Curious Case of Benign Memorization ICLR 2023