题  目：隐私保护约束下多源数据融合建模方法及应用

主讲人：方匡南教授，博士生导师，国家社科基金重大项目首席专家

内 容：It is increasingly common that financial data is distributed and with multiple individual sources (referred to as clients in some studies). Integrating raw data, although powerful, is often not feasible, for example, when there are considerations on privacy protection. Distributed learning techniques have been developed to integrate summary statistics as opposed to raw data. In many of the existing distributed learning studies, it is stringently assumed that all the clients have the same model. To accommodate data heterogeneity, some federated learning methods allow for client-specific models. In this article, we consider the scenario that clients form clusters, those in the same cluster have the same model, and different clusters have different models. Further considering the clustering structure can lead to a better understanding of the interconnections among clients and reduce the number of parameters. To this end, we develop a novel penalization approach. Specifically, group penalization is imposed for regularized estimation  and selection of important variables, and fusion penalization is imposed to automatically cluster clients. An effective ADMM algorithm is developed, and the estimation, selection, and clustering consistency properties are established under mild conditions. Simulation and data analysis further demonstrate the practical utility and superiority of the proposed approach.

时  间：2023年10月13日15:00-16:30

地  点：9-326

主讲人简介：方匡南，厦门大学西汉姆联赞助商必威app首页统计学与数据科学系教授、博士生导师、耶鲁大学博士后，厦门大学西汉姆联赞助商必威app首页统计学与数据科学系副主任，厦门大学信用大数据与智能风控研究中心主任，国际统计学会 elected member，国家社科基金重大项目首席专家。主要从事统计机器学习、经济管理统计、金融科技等。入选国家级高层次青年人才、福建省高层次人才A类等。兼全国工业统计教学研究会副会长、中国商业统计学会常务理事、《统计研究》、《数理统计与管理》编委等。在国内外权威期刊共发表学术论文100余篇论文，著有学术专著和教材等6部。