报告题目：Statistical Learning Theory for Contrastive Representation Learning

报告人：应益明教授，SUNY Albany

报告时间：2023年12月8日（周五）10:30-11:30

报告地点：腾讯会议ID：210-356-418

报告摘要：In this talk, I will review the background of Contrastive Representation Learning (CRL) and discuss the recent progress in establishing its learning theory foundation. CRL has demonstrated impressive empirical performance as a self-supervised learning model, surpassing even supervised learning models in various domains like computer vision and natural language processing. The talk addresses two crucial theoretical questions: (1) How does the generalization behavior of downstream tasks benefit from the representation function built from CRL? (2) Particularly, how does the number of negative (dissimilar) examples impact its learning performance? Our analysis reveals that generalization bounds for contrastive learning are not dependent on the number of negative examples, up to logarithmic terms. This analysis utilizes structural results on empirical covering numbers and Rademacher complexities to exploit the Lipschitz continuity of loss functions.

报告人简介：Yiming Ying is a Professor at SUNY Albany and the founding director of ML@UAlbany, a machine learning lab at UAlbany. His research focuses on Statistical Learning Theory, Trustworthy Machine Learning, and Optimization for Machine Learning. Dr. Ying is the recipient of the University at Albany's Presidential Award for Excellence in Research and Creative Activities (2022) and the SUNY Chancellor's Award for Excellence in Scholarship and Creative Activities (2023). He serves as an associate editor for several journals such as Transactions of Machine Learning Research, Neurocomputing, and Mathematical Foundation of Computing, and as an Area Chair for major machine learning conferences such as NeurIPS, ICML, and AISTATS.

邀请人：向道红