 On the generalization of learning algorithms that do not convergeNeural Information Processing Systems (NeurIPS), 2022 |
 Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of
Representation Learning in Actor-CriticNeural Information Processing Systems (NeurIPS), 2021 |
 One-pass Stochastic Gradient Descent in Overparametrized Two-layer
Neural NetworksInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Hanjing Zhu Hanjing Zhu |
 Predicting the outputs of finite deep neural networks trained with noisy
gradientsPhysical Review E (PRE), 2020 |
 Landscape Connectivity and Dropout Stability of SGD Solutions for
Over-parameterized Neural NetworksInternational Conference on Machine Learning (ICML), 2019 |
