Talks and Presentations

  1. A Quasistatic Derivation of Optimization Algorithms' Exploration on the Manifold of Minima, AMS 2022 Fall Western Sectional Meeting: upcoming on 10/22/2022

  2. Implicit bias of optimization algorithms for neural networks: static and dynamic perspectives, Math Machine Learning seminar MPI MIS + UCLA, 10/2022

  3. Implicit biases of optimization algorithms for neural networks and their effects on generalization, University of California, Berkeley, 10/2022

  4. Implicit biases of optimization algorithms for neural networks and their effects on generalization, Shanghai Jiao Tong University, 10/2022

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

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

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

  8. 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

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

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

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

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

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

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

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

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

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