Learning Theory

Revisiting Weighted Strategy for Non-stationary Parametric Bandits AISTATS 2023 Reward-Mixing MDPs with Few Latent Contexts are Learnable ICML 2023 Rigorously Assessing Natural Language Explanations of Neurons EMNLP 2023 Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function Approximation ICLR 2023 Risk Bounds for Positive-Unlabeled Learning Under the Selected At Random Assumption JMLR 2023 Risk Bounds on Aleatoric Uncertainty Recovery AISTATS 2023 Robust Budget Pacing with a Single Sample ICML 2023 Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity NeurIPS 2023 Robust Empirical Risk Minimization with Tolerance ALT 2023 Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization CVPR 2023 Robust Learning with Progressive Data Expansion Against Spurious Correlation NeurIPS 2023 Robust Lipschitz Bandits to Adversarial Corruptions NeurIPS 2023 Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023 Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data UAI 2023 Sample Complexity Bound for Evaluating the Robust Observer’s Performance under Coprime Factors Uncertainty L4DC 2023 Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes ICML 2023 Sample Complexity for Distributionally Robust Learning under chi-square divergence JMLR 2023 Sample Complexity of Distinguishing Cause from Effect AISTATS 2023 Sample Complexity of Forecast Aggregation NeurIPS 2023 Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks ICLR 2023 Sample Complexity of Probability Divergences under Group Symmetry ICML 2023 Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds NeurIPS 2023 Sample Efficiency of Data Augmentation Consistency Regularization AISTATS 2023 Scalable Performance Analysis for Vision-Language Models ACL 2023 Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel ICLR 2023