Simon Shaolei Du 杜少雷

Simon Shaolei Du 

Simon Shaolei Du
Email: ssdu [at] cs (dot) washington (dot) edu
Office: Gates 312
Google Scholar / DBLP / Talk Bio
Twitter

About Me

I am an assistant professor in the Paul G. Allen School of Computer Science & Engineering at University of Washington. My research interests are broadly in machine learning such as deep learning, representation learning and reinforcement learning.

Prior to starting as faculty, I was a postdoc at Institute for Advanced Study of Princeton, hosted by Sanjeev Arora. I completed my Ph.D. in Machine Learning at Carnegie Mellon University, where I was co-advised by Aarti Singh and Barnabás Póczos. Previously, I studied EECS and EMS at UC Berkeley. I have also spent time at Simons Institute and research labs of Facebook, Google and Microsoft.

Students and Visitors

My current focus is on theoretical foundations of deep learning, representation learning and (multi-agent) reinforcement learning.
I am looking for PhD students starting from Fall 2024.
I am happy to host (remote) undergradaute / graduate visitors.
If you want to work with me, please feel free to send me an email with your CV.

Research Focus and Selected Publications

Representation Learning Theory

We studied when pretraining provably improves the performance of the downstream task. Based on our theory, we developed an active learning algorithm to select the most relevant pretraining data.

Optimization and Generalization in Over-Parameterized Neural Networks

We proved the first set of global optimization and generalization guarantees for over-parameterized neural networks in the neural tanget kernel regime [Wikipedia]. Also see our [Blog] for a quick sumary. Recently, we found over-parameterization can exponentially slow down convergence.

Reinforcement Learning with Function Approximation

We studied the necessary and sufficient conditions that permit efficient learning for reinforcement learning problems with a large state space.

Multi-Agent Reinforcement Learning (MARL)

We initiated the study on what dataset permits solving offline reinforcement learning problems. We also study MARL with function approximation that avoids the exponential dependency on the # of agents.

Fundamental Limits of Reinforcement Learning

We develop algorithms to obtain optimal complexity guarantees for reinforcement learning. In particular, we showed the sample complexity can be independent of the planning horizon.

Acknowledgement: National Science Foundation (Awards 2212261, 2143493, 2134106, 2019844, 2110170, 2229881), NEC, Tencent, UW eScience.