154.com皇冠学术报告

Subsampling and subdata selection for generalized linear models

虞俊

（北京理工大学数学与统计学院）

报告时间：2023年10月26日 星期四 下午15:00-16:00

报告地点：沙河校区E404  

报告摘要：Subsampling focuses on selecting a subsample that can efficiently sketch the information of the original data in terms of statistical inference. It provides a powerful tool in big data analysis and gains the attention of data scientists in recent years. In this talk, we summarize some subsampling methods inspired by statistical design for analyzing generalized linear model. The relationships between designs and the related subsampling approaches are discussed. Specifically, two major families of design-inspired subsampling techniques are presented. The first aims to select a subsample following some optimal design criteria, while the second tries to find a subsample that meets some design structures. Some possible applications of subsampling will be presented.

报告人简介：虞俊，北京理工大学助理教授。主要从事试验设计、大数据抽样相关研究，在JASA、Statistica Sinica, Journal of machine learning research, NeurIPS等顶级期刊，会议发表多篇学术论文。

邀请人：谢家新，黄猛