CSCI 591 Colloquium: Prof. Yisen Wang (Peking University) - Theoretical Understanding of Self-Supervised Learning

Speaker: Yisen Wang, Peking University

Talk Title: Theoretical Understanding of Self-Supervised Learning

Abstract: Self-supervised learning (SSL) is an unsupervised approach for representation learning without relying on human-provided labels. It creates auxiliary tasks on unlabeled input data and learns representations by solving these tasks. SSL has demonstrated great success on various tasks. The existing SSL research mostly focuses on improving the empirical performance without a theoretical foundation. While the proposed SSL approaches are empirically effective on benchmarks, they are not well understood from a theoretical perspective. In this talk, I will introduce a series of our recent work on theoretical understanding of SSL, particularly on contrastive learning and masked autoencoders.     This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Yisen Wang is an assistant professor at Peking University. His research interests include machine learning theory and algorithms, focusing on adversarial robustness, graph learning, and weak/self-supervised learning theory. He has published more than 50 top academic papers in the field of machine learning, including ICML, NeurIPS, ICLR, etc., and many of them have been selected as Oral or Spotlight. He has won the ECML 2021 Best Paper Award.

Host: Yue Zhao

More Info: https://usc.zoom.us/j/97892066727?pwd=LytmZmltbDk5aWZtZHdKTjZyclI1QT09

Location: Ronald Tutor Hall of Engineering (RTH) - 109

Audiences: Everyone Is Invited

Contact: Chair's Assistant

Event Link: https://usc.zoom.us/j/97892066727?pwd=LytmZmltbDk5aWZtZHdKTjZyclI1QT09