报告题目：On Algorithmic Stability and Robustness of Bootstrap SGD

报告人：Professor Andreas Christmann，University of Bayreuth, Germany

报告时间：2025年5月22日（周四）14:30-15:30

报告地点：20-200

报告摘要：The bootstrap is a computer-based resampling method that can provide good approximations to the finite sample distribution of a given statistic. In this talk some methods to use the empirical bootstrap approach for stochastic gradient descent (SGD) to minimize the empirical risk over a Hilbert space are investigated from the view point of algorithmic stability and statistical robustness. Two types of approaches are based on averages and are investigated from a theoretical point of view. Another type of bootstrap SGD is proposed to demonstrate that it is possible to construct purely distribution-free pointwise confidence intervals and  distribution-free pointwise tolerance intervals of the median curve using bootstrap SGD.

This is joint work with Prof. Junwen LEI (The University of Hong Kong).

报告人简介：Andreas Christmann received a Ph.D degree from University of Dortmund, Germany. After positions as professor at KUL in Leuven and at VUB in Brussels (both in Belgium), he is a Full Professor and Chair for Stochastics and Machine Learning in the Department of Mathematics, University of Bayreuth, Germany. His research interests include statistical learning theory, kernel methods, robust statistics, and statistical methods for big data. He has published many research papers and 1 monograph entitled “Support Vector Machine” in these areas. He is an Action Editor for “Journal of  Machine Learning Research” from 2013 to 2019.  Since 2020, he is the member of the JMLR Editorial board of reviewers.

邀请人：向道红