Talks and Presentations

  1. Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes, Princeton University, 07/2022

  2. Nonlocal Behavior of Neural Network Loss Landscape, ML Foundations seminar, Microsoft research, 05/2022

  3. On the linear stability of SGD and input smoothness of neural networks, Theoretically Inclined Machine Learning (TML) Seminar, University of Ottawa, 02/2022

  4. Provably convergent quasistatic dynamics for mean-field two-player zero-sum games, Optimal transport and Mean field games Seminar, University of South Carolina, 01/2022

  5. Provably convergent quasistatic dynamics for mean-field two-player zero-sum games, Stanford Applied Math Seminar, 01/2022

  6. A qualitative study of the dynamic behavior of adaptive gradient algorithms, Mathematical and Scientific Machine Learning, 08/2021

  7. The Sobolev Regularization Effect of Stochastic Gradient Descent, BAAI Conference, 06/2021

  8. A Qualitative Study of the Dynamic Behavior of Adaptive Gradient Algorithms, symposium on machine learning and dynamical systems, 09/2020

  9. The Slow Deterioration of the Generalization Error of the Random Feature Model, UC Berkeley, 09/2020

  10. The Slow Deterioration of the Generalization Error of the Random Feature Model, MSML 2020, 07/2020

  11. A-priori Estimates of Population Risks for Neural Networks Models, Shanghai Jiao Tong University, 03/2020

  12. A-priori estimates of population risks for neural networks models, Chinese Academy of Sciences, 07/2019

  13. Appropriate function spaces for two-layer neural network and residual network models, Peking University, 06/2019