Learning Theory

A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning ICLR 2022 A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds ICML 2022 A Regret-Variance Trade-Off in Online Learning NeurIPS 2022 A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits NeurIPS 2022 A Simple and Optimal Policy Design for Online Learning with Safety against Heavy-tailed Risk NeurIPS 2022 A spectral-based analysis of the separation between two-layer neural networks and linear methods JMLR 2022 Assessing Combinational Generalization of Language Models in Biased Scenarios AACL 2022 Asymptotically-Optimal Gaussian Bandits with Side Observations ICML 2022 Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits AISTATS 2022 A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features ICLR 2022 A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization ICML 2022 A Theoretical Framework for Inference Learning NeurIPS 2022 A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning NeurIPS 2022 A Theory of PAC Learnability under Transformation Invariances NeurIPS 2022 A theory of weight distribution-constrained learning NeurIPS 2022 Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems NeurIPS 2022 A Unified View on PAC-Bayes Bounds for Meta-Learning ICML 2022 A Unifying Framework for Online Optimization with Long-Term Constraints NeurIPS 2022 AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning NeurIPS 2022 A Worst Case Analysis of Calibrated Label Ranking Multi-label Classification Method JMLR 2022 BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NeurIPS 2022 BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation CoRL 2022 Benchmarking Compositionality with Formal Languages COLING 2022 Benefits of Additive Noise in Composing Classes with Bounded Capacity NeurIPS 2022 Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint ICML 2022