报告主题：Range Penalization: Theoretical Insights with Applications in Federated Learning

时间：2025年5月21日15:30-16:30

地点：上川路校区一教218 

报告人：佘轶原

报告内容简介：

This talk introduces range regularization to enhance statistical accuracy and transmission efficiency, essential for reducing communication and computational demands in federated learning without compromising performance. Our approach identifies features with shared weights across different clients and adaptively clusters the weights of personalized features at extreme values, a process we refer to as polar clustering. Theoretical analysis of the associated estimators poses significant challenges due to the seminorm nature and non-decomposability of the regularizer. We develop new proof techniques for the nonasymptotic analysis of statistical accuracy and faithful pattern recovery. Moreover, a fast optimization algorithm that leverages varying degrees of local strong convexity is proposed to reduce iteration complexity. Experiments support the efficacy and efficiency of our approach.

主讲人简介：

佘轶原于2008年获得斯坦福大学统计学博士学位，早年在北京大学获得学士与硕士学位。此后，他在佛罗里达州立大学统计系任教。曾获美国国家科学基金会职业生涯奖（NSF CAREER Award），并当选为美国统计学会（ASA）会士、数理统计学会（IMS）会士，以及国际统计学会（ISI）当选会员。2025年起，他加入西湖大学理论科学研究院。