 Time-Independent Information-Theoretic Generalization Bounds for SGLDNeural Information Processing Systems (NeurIPS), 2023 |
 PAC-Bayes Compression Bounds So Tight That They Can Explain
GeneralizationNeural Information Processing Systems (NeurIPS), 2022 |
 Stability and Generalization Analysis of Gradient Methods for Shallow
Neural NetworksNeural Information Processing Systems (NeurIPS), 2022 |
 |
 Learning with Gradient Descent and Weakly Convex LossesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex
LearningInternational Conference on Learning Representations (ICLR), 2019 |
 Non-convex learning via Stochastic Gradient Langevin Dynamics: a
nonasymptotic analysisAnnual Conference Computational Learning Theory (COLT), 2017 |
 Rényi Divergence and Kullback-Leibler DivergenceIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2012 |
