Lei Wu (吴磊)

Assistant Professor School of Mathematical Sciences Center for Machine Learning Research Peking University Office: 静园6院 205 Email: leiwu (at) math (dot) pku (dot) edu (dot) cn Google Scholar     Github

About Me

I am currently an Assistant Professor in the School of Mathematical Sciences and Center for Machine Learning Research at Peking University.

Previously, I was a postdoc in PACM at Princeton University and in the Wharton Statistics and Data Science Department at the University of Pennsylvania. I completed my Ph.D. in computational mathematics at Peking University in 2018, advised by Prof. Weinan E. I received my B.S. degree in mathematics from Nankai University in 2012.

My current research focuses on understanding the mechanisms behind machine and deep learning, specifically:

• The approximation and representation power of neural networks

• The convergence and implicit bias of optimization algorithms like SGD and Adam

• The emergent phenomena observed in the training of foundation models

Recruiting

We are actively seeking self-motivated postdocs, PhD students and interns to join our team, particularly those with backgrounds in computer science and physics. If you are interested in collaborating with me, please send an email to me with your CV and transcript as well as a brief description of your research interests.

Selected Publications

• Theoretical analysis of inductive biases in deep convolutional networks
  Zihao Wang, Lei Wu
  NeurIPS 2023.

• A duality framework for analyzing random feature and two-layer neural networks
  (α-β) Hongrui Chen, Jihao Long, Lei Wu
  arXiv preprint, 2023.

• The implicit regularization of dynamical stability in stochastic gradient descent
  Lei Wu, Weijie J. Su
  ICML 2023.

• The alignment property of SGD noise and how it helps select flat minima: A stability analysis
  Lei Wu, Mingze Wang, Weijie J. Su
  NeurIPS 2022.

• The Barron space and flow-induced function spaces for neural network models
  (α-β) Weinan E, Chao Ma, Lei Wu
  Constructive Approximation, 2021.

• A comparative analysis of the optimization and generalization property of two-layer neural network and random feature models under gradient descent dynamics
  (α-β) Weinan E, Chao Ma, Lei Wu
  Science China Mathematics, 2020.

• How SGD selects the global minima in over-parameterized learning: A dynamical stability perspective
  Lei Wu, Chao Ma, Weinan E
  NeurIPS 2018.