Learning Theory

Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning JMLR 2022 Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity ICML 2022 Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design NeurIPS 2022 Instance Dependent Regret Analysis of Kernelized Bandits ICML 2022 Instance-optimal PAC Algorithms for Contextual Bandits NeurIPS 2022 Inter-annotator agreement is not the ceiling of machine learning performance: Evidence from a comprehensive set of simulations ACL 2022 Interpolating Predictors in High-Dimensional Factor Regression JMLR 2022 Intrinsic Dimension Estimation Using Wasserstein Distance JMLR 2022 Invariance-Aware Randomized Smoothing Certificates NeurIPS 2022 Inverse Contextual Bandits: Learning How Behavior Evolves over Time ICML 2022 Investigating and Explaining the Frequency Bias in Image Classification IJCAI 2022 Investigating Generalization by Controlling Normalized Margin ICML 2022 Investigating Why Contrastive Learning Benefits Robustness against Label Noise ICML 2022 In What Ways Are Deep Neural Networks Invariant and How Should We Measure This? NeurIPS 2022 Is a Modular Architecture Enough? NeurIPS 2022 Is Out-of-Distribution Detection Learnable? NeurIPS 2022 Is Sortition Both Representative and Fair? NeurIPS 2022 Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments NeurIPS 2022 KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-zero Training Loss AAAI 2022 Kernel interpolation in Sobolev spaces is not consistent in low dimensions COLT 2022 k-experts - Online Policies and Fundamental Limits AISTATS 2022 KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints JMLR 2022 Knowledge Distillation: Bad Models Can Be Good Role Models NeurIPS 2022 Label Ranking through Nonparametric Regression ICML 2022 Lattice-Based Methods Surpass Sum-of-Squares in Clustering COLT 2022