Learning Theory

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data ICLR 2019 On the number of variables to use in principal component regression NeurIPS 2019 On the optimality of the Hedge algorithm in the stochastic regime JMLR 2019 On the Power and Limitations of Random Features for Understanding Neural Networks NeurIPS 2019 On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length ICLR 2019 On the Spectral Bias of Neural Networks ICML 2019 On the Value of Target Data in Transfer Learning NeurIPS 2019 Open Problem: Do Good Algorithms Necessarily Query Bad Points? COLT 2019 Open Problem: How fast can a multiclass test set be overfit? COLT 2019 Open Problem: Is Margin Sufficient for Non-Interactive Private Distributed Learning? COLT 2019 Open Problem: Monotonicity of Learning COLT 2019 Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory COLT 2019 Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards ICML 2019 Optimal Best Markovian Arm Identification with Fixed Confidence NeurIPS 2019 Optimal Collusion-Free Teaching ALT 2019 Optimality Implies Kernel Sum Classifiers are Statistically Efficient ICML 2019 Optimal Transport: Fast Probabilistic Approximation with Exact Solvers JMLR 2019 Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions NeurIPS 2019 Optimizing in the Dark: Learning an Optimal Solution through a Simple Request Interface AAAI 2019 Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback NeurIPS 2019 Order Optimal One-Shot Distributed Learning NeurIPS 2019 PAC-Bayes under potentially heavy tails NeurIPS 2019 PAC-Bayes Un-Expected Bernstein Inequality NeurIPS 2019 PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits ICML 2019 PAC Learnability of Node Functions in Networked Dynamical Systems ICML 2019