报告题目：Hierarchical Change-Point Detection for Multivariate Time Series via a Ball Detection Function

报告人：王学钦  中山大学  教授 

报告时间：2019年3月21日（周四） 上午 10: 00

报告地点：教学楼 SB203

报告摘要：

Sequences of random objects arise from many real applications, including high throughput omic data and  functional imaging data. Those sequences are usually dependent, non-linear, or even Non-Euclidean, and an important problem is  change-point detection in such dependent sequences in Banach spaces or metric spaces. The problem usually  requires the accurate inference for not only whether changes might have occurred but also the locations of the changes when they did occur. To this end, we first introduce a Ball detection function and show that it reaches its maximum at the change-point if a sequence has only one change point. Furthermore, we propose a  consistent estimator of  Ball detection function based on which we develop a hierarchical algorithm to detect all possible change points. We prove that the estimated change-point locations are consistent.  Our procedure can  estimate the number of change-points and detect their locations {\color{red}without assuming any} particular types of change-points as a change can occur in a sequence in different ways.  Extensive simulation studies and analyses of two interesting real datasets wind direction and Bitcoin price  demonstrate that our method has considerable advantages over existing competitors, especially when data are non-Euclidean or when there are distributional changes in the variance.

报告人简介：

王学钦博士现为中山大学数学学院和中山医学院教授，担任中山大学统计学科带头人，数学学院院长助理，中山大学华南统计科学研究中心执行主任等职。2003年毕业于纽约州立大学宾厄姆顿分校（Binghamton University）, 2012年入选教育部新世纪优秀人才支持计划学者， 2013年获得国家优秀青年研究基金，2014年入选第八批广东省高等学校“千百十工程”国家级培养计划，2016年入选“广东特支计划”（百千工程领军人才）。此外，他还担任教育部高等学校统计学类专业教学指导委员会委员、统计学国际期刊JASA（ACS）、《SII》、《JCS》的副主编和高等教育出版社《Lecture Notes: Data Science, Statistics and Probability》系列丛书的副主编等。 主要从事精准医疗、非参数统计、和机器学习等方面的研究。目前已经在包括统计学顶级刊物AOS、JASA和nature genetics等在内的国际学术期刊上发表SCI论文60余篇。