Learning Theory

On the Statistical Benefits of Curriculum Learning ICML 2022 On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL NeurIPS 2022 On the Uncomputability of Partition Functions in Energy-Based Sequence Models ICLR 2022 Open Problem: Do you pay for Privacy in Online learning? COLT 2022 Open Problem: Finite-Time Instance Dependent Optimality for Stochastic Online Learning with Feedback Graphs COLT 2022 Open Problem: Optimal Best Arm Identification with Fixed-Budget COLT 2022 Open Problem: Properly learning decision trees in polynomial time? COLT 2022 Open Problem: Regret Bounds for Noise-Free Kernel-Based Bandits COLT 2022 Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits ICML 2022 Optimal Binary Classification Beyond Accuracy NeurIPS 2022 Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond AISTATS 2022 Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits AISTATS 2022 Optimal SQ Lower Bounds for Learning Halfspaces with Massart Noise COLT 2022 Optimal SQ Lower Bounds for Robustly Learning Discrete Product Distributions and Ising Models COLT 2022 Optimal Weak to Strong Learning NeurIPS 2022 Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees NeurIPS 2022 Optimization and Adaptive Generalization of Three layer Neural Networks ICLR 2022 Optimization-Based Separations for Neural Networks COLT 2022 Oracle Complexity in Nonsmooth Nonconvex Optimization JMLR 2022 Oracle-Efficient Online Learning for Smoothed Adversaries NeurIPS 2022 Orchestrated Value Mapping for Reinforcement Learning ICLR 2022 Out-of-Distribution Generalization With Causal Invariant Transformations CVPR 2022 Overparameterization from Computational Constraints NeurIPS 2022 PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization NeurIPS 2022 PAC Guarantees and Effective Algorithms for Detecting Novel Categories JMLR 2022