Passive and Active Multi-Task Representation Learning
Simon S. Du
https://umd.zoom.us/j/95197245230?pwd=cDRlVWRVeXBHcURGQkptSHpIS0VGdz09
Abstract
Representation learning has been widely used in many applications. In this talk, I will present our work which uncovers when and why representation learning provably improves the sample efficiency, from a statistical learning point of view. Furthermore, I will talk about how to actively select the most relevant task to boost the performance.
Relevant papers: https://arxiv.org/abs/2202.00911 https://arxiv.org/abs/2002.09434
Bio
Simon S. Du is an assistant professor in the Paul G. Allen School of Computer Science & Engineering at University of Washington. His research interests are broadly in machine learning such as deep learning, representation learning and reinforcement learning. Prior to starting as faculty, he was a postdoc at Institute for Advanced Study of Princeton. He completed his Ph.D. in Machine Learning at Carnegie Mellon University. Previously, he studied EECS and EMS at UC Berkeley. He has also spent time at Simons Institute and research labs of Facebook, Google and Microsoft. He has received NSF CAREER award, WAIC Yunfan Award and AAAI New Faculty Highlights.
This talk is organized by Richa Mathur