Learning Theory

Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs NeurIPS 2023 Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles AISTATS 2023 Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems ALT 2023 Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts NeurIPS 2023 From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks COLT 2023 From Pseudorandomness to Multi-Group Fairness and Back COLT 2023 From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks ICML 2023 From Tempered to Benign Overfitting in ReLU Neural Networks NeurIPS 2023 Fundamental Limits in Formal Verification of Message-Passing Neural Networks ICLR 2023 Fundamental limits on the robustness of image classifiers ICLR 2023 Fundamental Tradeoffs in Learning with Prior Information ICML 2023 Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits AISTATS 2023 Generalization Analysis for Contrastive Representation Learning ICML 2023 Generalization and Estimation Error Bounds for Model-based Neural Networks ICLR 2023 Generalization Bounds for Adversarial Contrastive Learning JMLR 2023 Generalization Bounds for Adversarial Metric Learning IJCAI 2023 Generalization bounds for neural ordinary differential equations and deep residual networks NeurIPS 2023 Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels JMLR 2023 Generalization Bounds using Data-Dependent Fractal Dimensions ICML 2023 Generalization error bounds for multiclass sparse linear classifiers JMLR 2023 Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage COLT 2023 Generalization Guarantees of Self-Training of Halfspaces under Label Noise Corruption IJCAI 2023 Generalization Guarantees via Algorithm-dependent Rademacher Complexity COLT 2023 Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion AISTATS 2023 Generalization on the Unseen, Logic Reasoning and Degree Curriculum ICML 2023