• >
  • >
  • >
  • >
  • >
Lei Wu
Mathematical Sciences
Peking University
Beijing
Language: Chinese, English
Contact
Deep Learning Mathematics Neural Networks Optimization Gradient Descent Generalization Two-Layer Networks Random Features Population Risk Dynamical Stability
Areas of Focus
  • Mathematical theories of deep learning
Work Experience
  • 2021.12-present - Peking University - Assistant Professor
  • 2021.8-2021.11 - University of Pennsylvania - Postdoctoral Researcher
  • 2018.11-2021.7 - Princeton University - Postdoctoral Researcher
Academic Background & Achievements
  • 2019 PhD: Peking University
  • 2012 Bachelor: Nankai University
Publications
  • Machine Learning from a Continuous Viewpoint, Weinan E, Chao Ma, Lei Wu, 2020
  • Barron spaces and flow-induced function spaces for neural network models, Weinan E, Chao Ma, Lei Wu, 2021
  • A comparative analysis of the optimization and generalization property of two-layer neural network and random feature models under gradient descent dynamics, Weinan E, Chao Ma, Lei Wu, 2020
  • A priori estimates of the population risk for two-layer neural networks, Weinan E, Chao Ma, Lei Wu, 2019
  • How SGD selects the global minima in over-parameterized learning: A dynamical stability perspective, Lei Wu, Chao Ma, Weinan E, 2018
Post a Project

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that AGP may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from AGP.
Submit

Thank you for your message!
We will contact you soon.