Learning Theory

A Model-Agnostic Randomized Learning Framework based on Random Hypothesis Subspace Sampling ICML 2022 A Model Selection Approach for Corruption Robust Reinforcement Learning ALT 2022 Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective NeurIPS 2022 An Analysis of Ensemble Sampling NeurIPS 2022 An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem NeurIPS 2022 An Efficient Minimax Optimal Estimator For Multivariate Convex Regression COLT 2022 An Empirical Analysis on the Vulnerabilities of End-to-End Speech Segregation Models Interspeech 2022 An Empirical Study of Memorization in NLP ACL 2022 A New Family of Generalization Bounds Using Samplewise Evaluated CMI NeurIPS 2022 An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear Programming ICML 2022 An Information-Theoretic Framework for Deep Learning NeurIPS 2022 An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022 A Non-asymptotic Analysis of Non-parametric Temporal-Difference Learning NeurIPS 2022 A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models NeurIPS 2022 An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization AISTATS 2022 A NON-PARAMETRIC REGRESSION VIEWPOINT : GENERALIZATION OF OVERPARAMETRIZED DEEP RELU NETWORK UNDER NOISY OBSERVATIONS ICLR 2022 Anonymous Bandits for Multi-User Systems NeurIPS 2022 Anytime Guarantees under Heavy-Tailed Data AAAI 2022 A PAC-Bayesian Generalization Bound for Equivariant Networks NeurIPS 2022 Approximately Equivariant Networks for Imperfectly Symmetric Dynamics ICML 2022 Approximate Top-m Arm Identification with Heterogeneous Reward Variances AISTATS 2022 Approximation and Learning with Deep Convolutional Models: a Kernel Perspective ICLR 2022 Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks JMLR 2022 A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes AAAI 2022 A Quantitative Geometric Approach to Neural-Network Smoothness NeurIPS 2022