Abstract: 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.

Biography: Yiyuan She earned his Ph.D. in Statistics from Stanford University. He then joined the Department of Statistics at Florida State University. Dr. She is a recipient of the NSF CAREER Award, a Fellow of the American Statistical Association, a Fellow of the Institute of Mathematical Statistics, and an Elected Member of the International Statistical Institute. His current research interests lie in high-dimensional statistics, statistical machine learning, robust statistics, and related fields. He currently serves as an associate editor for the Journal of the American Statistical Association (Theory and Methods) and Statistica Sinica. In 2025, he joined the Institute for Theoretical Sciences at Westlake University as a Chair Professor.