Learning Theory

A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning NeurIPS 2020 Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices COLT 2020 Asymptotics of Wide Networks from Feynman Diagrams ICLR 2020 Asynchronous Coagent Networks ICML 2020 A Theoretical Framework for Target Propagation NeurIPS 2020 At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? ICLR 2020 Automated Spectral Kernel Learning AAAI 2020 Bad Global Minima Exist and SGD Can Reach Them NeurIPS 2020 Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class NeurIPS 2020 BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance EMNLP 2020 Bessel Smoothing and Multi-Distribution Property Estimation COLT 2020 Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting ICML 2020 Best Arm Identification in Spectral Bandits IJCAI 2020 Best-item Learning in Random Utility Models with Subset Choices AISTATS 2020 Best Practices for Scientific Research on Neural Architecture Search JMLR 2020 Better Algorithms for Estimating Non-Parametric Models in Crowd-Sourcing and Rank Aggregation COLT 2020 Better depth-width trade-offs for neural networks through the lens of dynamical systems ICML 2020 Better Full-Matrix Regret via Parameter-Free Online Learning NeurIPS 2020 Beyond Lazy Training for Over-parameterized Tensor Decomposition NeurIPS 2020 Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples NeurIPS 2020 Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles ICML 2020 Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs NeurIPS 2020 Black-box Certification and Learning under Adversarial Perturbations ICML 2020 Boundary thickness and robustness in learning models NeurIPS 2020 Bounding the expected run-time of nonconvex optimization with early stopping UAI 2020