learning theory

McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds NeurIPS 2019 Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks JMLR 2019 On Communication Complexity of Classification Problems COLT 2019 On Learning Invariant Representations for Domain Adaptation ICML 2019 On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective NeurIPS 2019 On Mean Estimation for General Norms with Statistical Queries COLT 2019 On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition AISTATS 2019 On the Spectral Bias of Neural Networks ICML 2019 Open Problem: How fast can a multiclass test set be overfit? COLT 2019 Optimality Implies Kernel Sum Classifiers are Statistically Efficient ICML 2019 Optimizing in the Dark: Learning an Optimal Solution through a Simple Request Interface AAAI 2019 Pure Exploration with Multiple Correct Answers NeurIPS 2019 Sparse Kernel Regression with Coefficient-based ℓ_q-regularization JMLR 2019 The advantages of multiple classes for reducing overfitting from test set reuse ICML 2019 The information-theoretic value of unlabeled data in semi-supervised learning ICML 2019 Tight Lower Bounds on the VC-dimension of Geometric Set Systems JMLR 2019 Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals NeurIPS 2019 Train and Test Tightness of LP Relaxations in Structured Prediction JMLR 2019 Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution NeurIPS 2018 Approximation Guarantees for Adaptive Sampling ICML 2018 A Property Testing Framework for the Theoretical Expressivity of Graph Kernels IJCAI 2018 Chaining Mutual Information and Tightening Generalization Bounds NeurIPS 2018 Conference on Learning Theory 2018: Preface COLT 2018 Dimension-free Information Concentration via Exp-Concavity ALT 2018 Distribution-Specific Hardness of Learning Neural Networks JMLR 2018