Learning Theory

A Probabilistic Approach to Neural Network Pruning ICML 2021 A Provably Efficient Sample Collection Strategy for Reinforcement Learning NeurIPS 2021 Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization EMNLP 2021 A Regret Minimization Approach to Iterative Learning Control ICML 2021 Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense EACL 2021 ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks ICML 2021 A Sharp Analysis of Model-based Reinforcement Learning with Self-Play ICML 2021 Asymptotically Optimal Information-Directed Sampling COLT 2021 Asymptotics of Ridge(less) Regression under General Source Condition AISTATS 2021 A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix AISTATS 2021 A Theoretical Analysis of Fine-tuning with Linear Teachers NeurIPS 2021 A Theory of Heuristic Learnability COLT 2021 A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions ICML 2021 A Theory of Label Propagation for Subpopulation Shift ICML 2021 A Theory of the Risk for Optimization with Relaxation and its Application to Support Vector Machines JMLR 2021 A Topological Perspective on Causal Inference NeurIPS 2021 A Universal Law of Robustness via Isoperimetry NeurIPS 2021 Automated Symbolic Law Discovery: A Computer Vision Approach AAAI 2021 Average-Case Communication Complexity of Statistical Problems COLT 2021 Bandit algorithms: Letting go of logarithmic regret for statistical robustness AISTATS 2021 Bandit Phase Retrieval NeurIPS 2021 Bandits with Knapsacks beyond the Worst Case NeurIPS 2021 Bandits with many optimal arms NeurIPS 2021 Batch Value-function Approximation with Only Realizability ICML 2021 Bellman-consistent Pessimism for Offline Reinforcement Learning NeurIPS 2021