learning theory

A Proof That Using Crossover Can Guarantee Exponential Speed-Ups in Evolutionary Multi-Objective Optimisation AAAI 2023 Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation ICML 2023 A Theory of Dynamic Benchmarks ICLR 2023 A Theory of Multimodal Learning NeurIPS 2023 Benign Overfitting of Constant-Stepsize SGD for Linear Regression JMLR 2023 Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time NeurIPS 2023 Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff NeurIPS 2023 Certifiable Out-of-Distribution Generalization AAAI 2023 Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy NeurIPS 2023 Counterfactual Memorization in Neural Language Models NeurIPS 2023 Demystifying Disagreement-on-the-Line in High Dimensions ICML 2023 Does It Pay to Optimize AUC? AAAI 2023 Does Sparsity Help in Learning Misspecified Linear Bandits? ICML 2023 Error in the Euclidean Preference Model IJCAI 2023 Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification UAI 2023 Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods ICLR 2023 Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron ICML 2023 First- and Second-Order Bounds for Adversarial Linear Contextual Bandits NeurIPS 2023 Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization NeurIPS 2023 Hardness of Agnostically Learning Halfspaces from Worst-Case Lattice Problems COLT 2023 Hardness of Learning AES Key (Student Abstract) AAAI 2023 High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance ICML 2023 Hypothesis Selection with Memory Constraints NeurIPS 2023 Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning NeurIPS 2023 Inverse Scaling Can Become U-Shaped EMNLP 2023