Skip to main content

Simon Du

Simon Du

Research focus

deep learning, representation learning, reinforcement learning, non-convex optimization

Education

Ph.D. Computer Science, Carnegie Mellon University, 2019
B.S. Electrical Engineering and Computer Science, University of California, Berkeley, 2015
B.S. Engineering Mathematics and Statistics, University of of California, Berkeley, 2015

Simon Du joined the Allen School as an assistant professor in August 2020. Prior to joining the UW, Simon held a postdoctoral appointment at the Institute for Advanced Study at Princeton. He also spent time at the Simons Institute and research labs of Facebook, Google and Microsoft.

His research interests are in machine learning, specifically in theory and algorithm design, with the goal of improving accuracy and developing more end-user-friendly methods. Simon explores the foundations of deep learning and reinforcement learning to develop statistically efficient algorithms, design new classes of functions and improve their performance. His work has inspired a new class of machine learning models that can achieve state-of-the-art performance on various domains, from categorical data to social network data.