learning theory

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? ICLR 2020 Kernel Alignment Risk Estimator: Risk Prediction from Training Data NeurIPS 2020 k-means++: few more steps yield constant approximation ICML 2020 Learning Parities with Neural Networks NeurIPS 2020 Lower Bounds for Learning Distributions under Communication Constraints via Fisher Information JMLR 2020 Margins are Insufficient for Explaining Gradient Boosting NeurIPS 2020 Minimizing Dynamic Regret and Adaptive Regret Simultaneously AISTATS 2020 More Data Can Expand The Generalization Gap Between Adversarially Robust and Standard Models ICML 2020 Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals NeurIPS 2020 On Convergence and Generalization of Dropout Training NeurIPS 2020 On Performance Estimation in Automatic Algorithm Configuration AAAI 2020 On the limits of cross-domain generalization in automated X-ray prediction MIDL 2020 On the Theory of Transfer Learning: The Importance of Task Diversity NeurIPS 2020 On the universality of deep learning NeurIPS 2020 Open Problem: Tight Convergence of SGD in Constant Dimension COLT 2020 Optimal multiclass overfitting by sequence reconstruction from Hamming queries ALT 2020 PAC-Bayes Learning Bounds for Sample-Dependent Priors NeurIPS 2020 Phase Transitions for the Information Bottleneck in Representation Learning ICLR 2020 Refined bounds for algorithm configuration: The knife-edge of dual class approximability ICML 2020 Sample-Efficient Reinforcement Learning of Undercomplete POMDPs NeurIPS 2020 Sharper Bounds for Uniformly Stable Algorithms COLT 2020 Simultaneous Inference for Massive Data: Distributed Bootstrap ICML 2020 Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks NeurIPS 2020 Statistical Learning with a Nuisance Component (Extended Abstract) IJCAI 2020 Strength from Weakness: Fast Learning Using Weak Supervision ICML 2020