vc dimension

Towards a Unified Information-Theoretic Framework for Generalization NeurIPS 2021 A Limitation of the PAC-Bayes Framework NeurIPS 2020 Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples NeurIPS 2020 Decision trees as partitioning machines to characterize their generalization properties NeurIPS 2020 Open Problem: Information Complexity of VC Learning COLT 2020 PAC learning with stable and private predictions COLT 2020 Private Query Release Assisted by Public Data ICML 2020 Proper Learning, Helly Number, and an Optimal SVM Bound COLT 2020 Quantum Boosting ICML 2020 Reasoning About Generalization via Conditional Mutual Information COLT 2020 Smoothed Analysis of Online and Differentially Private Learning NeurIPS 2020 Towards a Combinatorial Characterization of Bounded-Memory Learning NeurIPS 2020 An Approach to One-Bit Compressed Sensing Based on Probably Approximately Correct Learning Theory JMLR 2019 A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes ALT 2019 Characterizing the Sample Complexity of Pure Private Learners JMLR 2019 Graph-based Discriminators: Sample Complexity and Expressiveness NeurIPS 2019 Learning from Weakly Dependent Data under Dobrushin’s Condition COLT 2019 Limits of Private Learning with Access to Public Data NeurIPS 2019 Model Selection via the VC Dimension JMLR 2019 Precision-Recall versus Accuracy and the Role of Large Data Sets AAAI 2019 Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models NeurIPS 2019 Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity NeurIPS 2019 VC Classes are Adversarially Robustly Learnable, but Only Improperly COLT 2019 A Direct Sum Result for the Information Complexity of Learning COLT 2018 Chaining Mutual Information and Tightening Generalization Bounds NeurIPS 2018