报告人：王若度 （University of Waterloo）

时间：2021年9月14日15:00开始

地址：理科楼LA107

摘要：False discovery rate control is one of the most popular criteria in selective inference, and the Benjamini-Hochberg (BH) procedure based on p-values has been the prominent methodology in this field. As an alternative to p-values, e-values (expectation-values) have gained attention as a measure of uncertainty, significance and evidence. In brief, e-values are realized by random variables with expectation at most one under the null; examples include betting scores, (point null) Bayes factors, likelihood ratios and stopped supermartingales. We discuss advantages and disadvantages of e-values versus p-values in single, multiple, online and collaborative hypothesis testing. We introduced the e-BH procedure, a natural analog of the BH procedure for FDR control. Unlike the usual BH procedure, the e-BH procedure controls the FDR at the desired level for any dependence structure between the e-values, allowing for wide applications, including multi-armed bandit testing problems. The talk is based on joint research projects with Vladimir Vovk (Royal Holloway), Aaditya Ramdas (Carnegie Mellon), and Neil Xu (Carnegie Mellon).

简介:Dr. Ruodu Wang is University Research Chair, Sun Life Fellow, and Associate Professor of Actuarial Science and Quantitative Finance at the University of Waterloo in Canada. He received his PhD in Mathematics (2012) from the Georgia Institute of Technology, after completing his Bachelor (2006) and Master’s (2009) degrees at Peking University. He holds editorial positions in leading journals in actuarial science and mathematical economics, including Co-Editor of the European Actuarial Journal, and Co-Editor of ASTIN Bulletin - The Journal of the International Actuarial Association. His scientific work has appeared in academic journals in various other fields, such as Management Science, Operations Research, The Annals of Statistics, Biometrika, The Annals of Applied Probability, Mathematical Finance, and Mathematics of Operations Research. He is an affiliated member of RiskLab at ETH Zurich. Among other international awards, he received the first SOA Actuarial Science Early Career Award in 2021 from the Society of Actuaries.

邀请人：张志民

欢迎广大师生积极参与！