Princeton University

School of Engineering & Applied Science

Jason D. Lee

Assistant Professor of Electrical Engineering


Room: B308 Engineering Quadrangle
Phone: 609-258-8396
Email: jasonlee@princeton.edu
Webpage: Jason Lee Group

Education

  • Ph.D., Computational and Mathematical Engineering, Stanford University, 2015
  • B.Sc., Mathematics, Duke University, 2010

Jason Lee received his PhD at Stanford University advised by Trevor Hastie and Jonathan Taylor in 2015. Before joining Princeton, he was a postdoctoral scholar at UC Berkeley with Michael I. Jordan, and an assistant professor at University of Southern California. His research interests are in machine learning, optimization, and statistics. Lately, he has worked on the foundations of deep learning, non-convex optimization, and reinforcement learning. He has received a Sloan Research Fellowship in 2019 and NIPS Best Student Paper Award for his work.

Honors and Awards

  • Sloan Research Fellowship in Computer Science
  • NIPS Best Student Paper Award

Selected Publications

  1. Gradient Descent Finds Global Minima of Deep Neural Networks. Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, and Xiyu Zhai. ICML 2019.

  2. Gradient Descent Converges to Minimizers. Jason D. Lee, Max Simchowitz, Michael I. Jordan, and Benjamin Recht. Conference on Learning Theory (COLT 2016).

  3. Matrix Completion has No Spurious Local Minimum. Rong Ge, Jason D. Lee, and Tengyu Ma. Neural Information Processing Systems (NIPS 2016)

  4. Theoretical insights into the optimization landscape of over-parameterized shallow neural networks. Mahdi Soltanolkotabi, Adel Javanmard, and Jason D. Lee. IEEE Transactions on Information Theory 2018.

  5. Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel. Colin Wei, Jason D. Lee, Qiang Liu, and Tengyu Ma.