时 间：2023年5月12日10:00-11:30
地 点：理科大楼A1514
报告人：杨朋昆清华大学助理教授
主持人：於州华东师范大学教授
摘 要：
Federated Learning is a promising framework that has great potentials in privacy preservation and in lowering the computation load at the cloud. The successful deployment faces many challenges in both theory and practice such as data heterogeneity and client unavailability. In this talk, I will discuss the resolution from a statistical perspective including the statistical efficiency of FedAvg and FedProx from a nonparametric regression viewpoint, and a new algorithm achieving global convergence when the clients exhibit cluster structure. A key innovation in our analysis is a uniform estimate on the clustering errors, which we prove by bounding the VC dimension of general polynomial concept classes based on the theory of algebraic geometry. I will also discuss the impact of adversarial client unavailability from a robust statistics perspective.
报告人简介：
Pengkun Yang is an assistant professor at the Center for Statistical Science at Tsinghua University. Prior to joining Tsinghua, he was a Postdoctoral Research Associate at the Department of Electrical Engineering at Princeton University. He received a Ph.D. degree (2018) and a master degree (2016) from the Department of Electrical and Computer Engineering at University of Illinois at Urbana-Champaign, and a B.E. degree (2013) from the Department of Electronic Engineering at Tsinghua University. His research interests include statistical inference, learning, optimization, and systems. He is a recipient of Thomas M. Cover Dissertation Award in 2020, and a recipient of Jack Keil Wolf ISIT Student Paper Award at the 2015 IEEE International Symposium on Information Theory (semi-plenary talk).