Learning Theory

Stochastic and Adversarial Online Learning without Hyperparameters NeurIPS 2017 Stochastic Rank-1 Bandits AISTATS 2017 Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues NeurIPS 2017 SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability NeurIPS 2017 The Complexity of Explaining Neural Networks Through (group) Invariants ALT 2017 The Condorcet Principle for Multiwinner Elections: From Shortlisting to Proportionality IJCAI 2017 The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits AISTATS 2017 The Power of Random Counterexamples ALT 2017 The Price of Differential Privacy for Online Learning ICML 2017 The Sample Complexity of Online One-Class Collaborative Filtering ICML 2017 The Sample Complexity of Optimizing a Convex Function COLT 2017 Tight Bounds for Bandit Combinatorial Optimization COLT 2017 Tight Bounds on ℓ_1 Approximation and Learning of Self-Bounding Functions ALT 2017 Towards Instance Optimal Bounds for Best Arm Identification COLT 2017 Understanding the Representation and Computation of Multilayer Perceptrons: A Case Study in Speech Recognition ICML 2017 Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning NeurIPS 2017 Unifying Task Specification in Reinforcement Learning ICML 2017 Variable Importance Using Decision Trees NeurIPS 2017 ZigZag: A New Approach to Adaptive Online Learning COLT 2017 A Closer Look at Adaptive Regret JMLR 2016 A Consistent Regularization Approach for Structured Prediction NeurIPS 2016 A Constant-Factor Bi-Criteria Approximation Guarantee for k-means++ NeurIPS 2016 Active Learning with Oracle Epiphany NeurIPS 2016 Actively Learning Hemimetrics with Applications to Eliciting User Preferences ICML 2016 Active Nearest-Neighbor Learning in Metric Spaces NeurIPS 2016