CHINA·77779193永利(集团)有限公司-Official website

题 目：Distributed Estimation on Semi-Supervised Generalized Linear

报告人：刘卫东 特聘教授（上海交通大学）

Abstract：Semi-supervised learning is devoted to using unlabeled data to improve the performance of machine learning algorithms. In this paper, we study the semi-supervised generalized linear model (GLM) in the distributed setup. In the cases of single or multiple machines containing the unlabeled data, we propose two distributed semi-supervised algorithms based on distributed approximate Newton method. When the labeled local sample size is small, our algorithms still give consistent estimation, while the fully supervised methods fail to converge. Moreover, we theoretically prove that the convergence rate is greatly improved when there are sufficient unlabeled data. Therefore the proposed method requires much fewer rounds of communications to achieve the optimal rate than its fully-supervised counterpart. In the case of the linear model, we prove the rate lower bound after one round communication, which shows that rate improvement is essential. Finally, several simulation analyses and real data studies are provided to demonstrate the effectiveness of our method.

报告人简介：刘卫东，上海交通大学特聘教授，国家杰出青年科学基金获得者，中国工业与应用数学学会理事。主要研究方向为统计学和机器学习等，目前已在AOS、 JASA、JRSSB、Biometrika、JMLR、ICML、IJCAI、IEEE TSP等专业顶尖期刊/会议上发表论文六十余篇。主持国家重点研发计划课题1项，国家杰出青年科学基金1项，国家优秀青年科学基金1项。

报告时间：2023年7月12日（周三）下午13:30-14:30

报告地点：首都师范大学本部校区教二楼 608

邀请人: 胡涛