Learning Theory

Non-Convex SGD Learns Halfspaces with Adversarial Label Noise NeurIPS 2020 Nonparametric Sequential Prediction While Deep Learning the Kernel AISTATS 2020 No-Regret and Incentive-Compatible Online Learning ICML 2020 No-Regret Exploration in Goal-Oriented Reinforcement Learning ICML 2020 No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix NeurIPS 2020 Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis ICML 2020 ODE-Inspired Analysis for the Biological Version of Oja’s Rule in Solving Streaming PCA COLT 2020 On Adaptivity in Information-Constrained Online Learning AAAI 2020 On Approximate Thompson Sampling with Langevin Algorithms ICML 2020 On Convergence and Generalization of Dropout Training NeurIPS 2020 On Efficiency in Hierarchical Reinforcement Learning NeurIPS 2020 On Efficient Adjustment in Causal Graphs JMLR 2020 One Size Fits All: Can We Train One Denoiser for All Noise Levels? ICML 2020 On Generalization Bounds of a Family of Recurrent Neural Networks AISTATS 2020 On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning ICLR 2020 On Learnability wih Computable Learners ALT 2020 On Learning Ising Models under Huber's Contamination Model NeurIPS 2020 Online Dense Subgraph Discovery via Blurred-Graph Feedback ICML 2020 Online Learning in Changing Environments IJCAI 2020 Online Learning with Continuous Variations: Dynamic Regret and Reductions AISTATS 2020 Online learning with dynamics: A minimax perspective NeurIPS 2020 Online Learning with Primary and Secondary Losses NeurIPS 2020 Online Linear Optimization with Many Hints NeurIPS 2020 Online Pricing with Offline Data: Phase Transition and Inverse Square Law ICML 2020 On Numerosity of Deep Neural Networks NeurIPS 2020