Jason Lee

Jason D. Lee is an associate professor of EECS and Statistics at UC Berkeley. Previously, he was a research scientist at Google Deepmind, a member of the IAS, and an associate professor at Princeton. Before that, he was a postdoc at UC Berkeley working with Michael I. Jordan. He received his PhD at Stanford advised by Trevor Hastie and Jonathan Taylor. He received a BS in Mathematics from Duke University advised by Mauro Maggioni.

Jason D. Lee is an Associate Professor of EECS & Statistics at UC Berkeley, known for his work in Machine Learning Theory, Artificial Intelligence, Statistics, and Optimization. His research focuses on understanding the theoretical foundations of machine learning algorithms, particularly in the context of deep neural networks, policy gradient methods, and optimization techniques. Lee's work explores the convergence properties of gradient descent, the existence of global minima, and the implicit bias of optimization algorithms. His publications also address challenges in distributed statistical inference, matrix completion, and the optimization landscape of over-parameterized models. His research has significant implications for improving the efficiency and reliability of machine learning systems.