报告题目: Data-driven selection of the number of change-points
报告人: 邹长亮 教授 南开大学
报告时间:2021年1月11日 13:30-14:20
报告地点:Zoom 会议 (Zoom 会议id: 770 311 8512, 密码: 378548)
校内联系人:王培洁 wangpeijie@jlu.edu.cn
报告摘要: In multiple change-point analysis, one of the main difficulties is to determine the number of change-points. In this talk, I will introduce a data-driven approach based on an order-preserved sample-splitting strategy. Under a unified framework, a cross-validation estimation scheme is developed to achieve consistent selection. Furthermore, we construct a simple yet effective selection procedure which can quantify “uncertainty”, say controlling certain error rate. The proposed methods are applicable to most kinds of popular change-point algorithms.
报告人简介:南开大学统计与数据科学学院教授。2008年于南开大学获博士学位,随后留校任教。主要从事统计学及其与数据科学领域的交叉研究和实际应用。研究兴趣包括:高维数据统计推断、大规模数据流分析、变点和异常点检测等,在Ann.Stat.、Biometrika、J.Am.Stat.Asso.、Math. Program.、Technometrics、IISE Tran.等统计学和工业工程领域期刊上发表论文几十篇,主持国家自然科学基金委重大项目课题、优青项目、杰青项目等。