1. Jason Lee Blogger
2. Jason London
3. Jason Lee Home Page

UPCOMING PERFORMANCES: Cinderella: Der Prinz Eduard von Winterstein Theater, Annaberg-Buchholz, DE 04., 07., 10., 24., 31. Oktober 2020 20., 22. Jason Lee - Home This site is dedicated to Economics 101 summer session II. You will find useful information and links.

About Me

I am an assistant professor of Electrical Engineering and Computer Science (secondary) in Princeton University and a member of the Theoretical Machine Learning Group. Previously, I was a member of the IAS and an assistant professor at USC for three years. Before that, I was a postdoc in the Computer Science Department at UC Berkeley working with Michael I. Jordan, and also collaborated with Ben Recht. I received my PhD in Applied Math advised by Trevor Hastie and Jonathan Taylor. I received a BS in Mathematics from Duke University advised by Mauro Maggioni.I am a native of Cupertino, CA.

My research interests are broadly in

• Foundations of Deep Learning (slides)(video)
  

• Representation Learning (slides)(video)
  

• Foundations of Deep Reinforcement Learning (slides)(video 1)(video 2)
  

Princeton PhD students interested in machine learning, statistics, or optimization research, please contact me; I advise students in Computer Science, Electrical Engineering, Math, ORFE, and PACM. I am recruiting PhD students and postdoctoral scholars starting in 2021 at Princeton University, please email me a CV apply.

My current focus is on machine learning with a focus on foundations of deep learning, reprsentation learning, and deep reinforcement learning. See my talk at MIT slides and video or my tutorial at the Simons Institute: tutorial slides and video.

I am also happy to host remote visitors. Summer visitors please contact me around February to schedule your visit. See a list of past visitors at here.

Awards

• Sloan Research Fellow in Computer Science, Alfred P. Sloan Foundation

• Finalist for Best Paper Prize for Young Researchers in Continuous Optimization

• ICML 2018 Workshop on Nonconvex Optimization for MLBest Paper Award for ‘‘Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced'

• NIPS 2016 Best Student Paper Award for ‘‘Matrix Completion has no Spurious Local Minima'.

Selected Publications

• Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot.
  Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, and Jason D. Lee.
  NeurIPS 2020.

• Predicting What You Already Know Helps: Provable Self-Supervised Learning.
  Jason D. Lee, Qi Lei, Nikunj Saunshi, and Jiacheng Zhuo.

• Towards Understanding Hierarchical Learning: Benefits of Neural Representations.
  Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, and Richard Socher.
  NeurIPS 2020.

• Few-Shot Learning via Learning the Representation, Provably.
  Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, and Qi Lei.

• Shape Matters: Understanding the Implicit Bias of the Noise Covariance.
  Jeff Z. HaoChen, Colin Wei, Jason D. Lee, and Tengyu Ma.
  

• Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks .
  Yu Bai and Jason D. Lee.
  ICLR 2020.

• On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
  Alekh Agarwal, Sham M. Kakade, Jason D. Lee, and Gaurav Mahajan.
  JMLR.

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

• Gradient Descent Converges to Minimizers.
  Jason D. Lee, Max Simchowitz, Michael I. Jordan, and Benjamin Recht.
  COLT 2016

• Matrix Completion has No Spurious Local Minimum.
  Rong Ge, Jason D. Lee, and Tengyu Ma.
  Best Student Paper Award at NeurIPS 2016.
  

• Exact Post-Selection Inference with the Lasso.
  Jason D. Lee, Dennis L Sun, Yuekai Sun, and Jonathan Taylor.
  Annals of Statistics 2016.
  

About Me

I am an assistant professor of Electrical Engineering and Computer Science (secondary) in Princeton University and a member of the Theoretical Machine Learning Group. Previously, I was a member of the IAS and an assistant professor at USC for three years. Before that, I was a postdoc in the Computer Science Department at UC Berkeley working with Michael I. Jordan, and also collaborated with Ben Recht. I received my PhD in Applied Math advised by Trevor Hastie and Jonathan Taylor. I received a BS in Mathematics from Duke University advised by Mauro Maggioni.I am a native of Cupertino, CA.

My research interests are broadly in

Jason Lee Blogger

• Foundations of Deep Learning (slides)(video)
  

• Representation Learning (slides)(video)
  

• Foundations of Deep Reinforcement Learning (slides)(video 1)(video 2)
  

Princeton PhD students interested in machine learning, statistics, or optimization research, please contact me; I advise students in Computer Science, Electrical Engineering, Math, ORFE, and PACM. I am recruiting PhD students and postdoctoral scholars starting in 2021 at Princeton University, please email me a CV apply.

My current focus is on machine learning with a focus on foundations of deep learning, reprsentation learning, and deep reinforcement learning. See my talk at MIT slides and video or my tutorial at the Simons Institute: tutorial slides and video.

I am also happy to host remote visitors. Summer visitors please contact me around February to schedule your visit. See a list of past visitors at here.

Awards

• Sloan Research Fellow in Computer Science, Alfred P. Sloan Foundation

• Finalist for Best Paper Prize for Young Researchers in Continuous Optimization

• ICML 2018 Workshop on Nonconvex Optimization for MLBest Paper Award for ‘‘Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced'

• NIPS 2016 Best Student Paper Award for ‘‘Matrix Completion has no Spurious Local Minima'.

Selected Publications

• Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot.
  Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Liwei Wang, and Jason D. Lee.
  NeurIPS 2020.

• Predicting What You Already Know Helps: Provable Self-Supervised Learning.
  Jason D. Lee, Qi Lei, Nikunj Saunshi, and Jiacheng Zhuo.

• Towards Understanding Hierarchical Learning: Benefits of Neural Representations.
  Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, and Richard Socher.
  NeurIPS 2020.

• Few-Shot Learning via Learning the Representation, Provably.
  Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, and Qi Lei.

• Shape Matters: Understanding the Implicit Bias of the Noise Covariance.
  Jeff Z. HaoChen, Colin Wei, Jason D. Lee, and Tengyu Ma.
  

Jason London

• Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks .
  Yu Bai and Jason D. Lee.
  ICLR 2020.

• On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
  Alekh Agarwal, Sham M. Kakade, Jason D. Lee, and Gaurav Mahajan.
  JMLR.

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

• Gradient Descent Converges to Minimizers.
  Jason D. Lee, Max Simchowitz, Michael I. Jordan, and Benjamin Recht.
  COLT 2016

• Matrix Completion has No Spurious Local Minimum.
  Rong Ge, Jason D. Lee, and Tengyu Ma.
  Best Student Paper Award at NeurIPS 2016.
  

Jason Lee Home Page

• Exact Post-Selection Inference with the Lasso.
  Jason D. Lee, Dennis L Sun, Yuekai Sun, and Jonathan Taylor.
  Annals of Statistics 2016.