learning theory

The Perils of Learning Before Optimizing AAAI 2022 Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints NeurIPS 2022 Towards Bridging Sample Complexity and Model Capacity AAAI 2022 Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective ICLR 2022 Towards Theoretically Grounded Evolutionary Learning IJCAI 2022 Towards Understanding the Mixture-of-Experts Layer in Deep Learning NeurIPS 2022 Universal Online Learning: an Optimistically Universal Learning Rule COLT 2022 What is a Good Metric to Study Generalization of Minimax Learners? NeurIPS 2022 When Hardness of Approximation Meets Hardness of Learning JMLR 2022 A Learning Theoretic Perspective on Local Explainability ICLR 2021 An Exact Characterization of the Generalization Error for the Gibbs Algorithm NeurIPS 2021 An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks NeurIPS 2021 A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions ICML 2021 A Theory of Label Propagation for Subpopulation Shift ICML 2021 Bandit algorithms: Letting go of logarithmic regret for statistical robustness AISTATS 2021 Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods ICLR 2021 Computational Separation Between Convolutional and Fully-Connected Networks ICLR 2021 Deciphering and Optimizing Multi-Task Learning: a Random Matrix Approach ICLR 2021 Dissecting Supervised Contrastive Learning ICML 2021 Domain Generalization by Marginal Transfer Learning JMLR 2021 Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations NeurIPS 2021 Fast rates for prediction with limited expert advice NeurIPS 2021 Few-Shot Learning via Learning the Representation, Provably ICLR 2021 Fine-grained Generalization Analysis of Structured Output Prediction IJCAI 2021 For self-supervised learning, Rationality implies generalization, provably ICLR 2021