题目：Clustered Federated Learning based on Nonconvex Pairwise Fusion

 报告人：孙怡帆

 摘要：This study investigates clustered federated learning (FL), one of the formulations of FL with non-i.i.d. data, where the devices are partitioned into clusters and each cluster optimally fits its data with a localized model. We propose a clustered FL framework that incorporates a nonconvex penalty to pairwise differences of parameters. Without a priori knowledge of the set of devices in each cluster and the number of clusters, this framework can autonomously estimate cluster structures. To implement the proposed framework, we introduce a novel clustered FL method called Fusion Penalized Federated Clustering (FPFC). Building upon the standard alternating direction method of multipliers (ADMM), FPFC can perform  partial updates at each communication round and allows parallel computation with variable workload. These strategies significantly reduce the communication cost while ensuring privacy, making it practical for FL. We also propose a new warmup strategy for hyperparameter tuning in FL settings and explore the asynchronous variant of FPFC (asyncFPFC). Theoretical analysis provides convergence guarantees for FPFC with general losses and establishes the statistical convergence rate under a linear model with squared loss. Extensive experiments have demonstrated the superiority of FPFC compared to current methods, including robustness and generalization capability.

报告人简介：孙怡帆，女，中国人民大学统计学院教授，博士生导师，数理统计系系主任，教育部人文社会科学重点研究基地应用统计研究中心研究员，全国工业统计学教学研究会常务理事、中国统计教育学会理事。主要研究方向为复杂数据分析、大数据分布式计算等，在Journal of Computational and Graphical Statistics、Statistics in Medicine、Physical Review X、AAAI等高水平学术期刊会议发表学术论文30余篇，主持国家自然科学基金、教育部人文社科基金，出版教材《数据科学优化方法》，获教学标兵、北京市高等教育教学成果一等奖等教学奖励。

 报告时间：4月15日（周一）上午10:00-11:00 

报告地点：教二楼627

 联系人：胡晓楠