报告题目: Deviation inequalities for stochastic approximation by averaging
报告人: 范协铨 副教授
报告人单位: 天津大学应用数学中心
报告日期: 2022年07月19日星期二
报告时间: 09:00准时开始
腾讯会议: 695-997-2875
邀请人: 褚为娟
报告摘要:We introduce a class of Markov chains that includes models of stochastic approximation by averaging and non-averaging. Using a martingale approximation method, we establish various deviation inequalities for separately Lipschitz functions of such a chain, with different moment conditions on some dominating random variables of martingale differences. Finally, we apply these inequalities to stochastic approximation by averaging. This talk is based on join work of Pierre Alquier, Jerome Dedecker and Paul Doukhan.
报告人简介: 范协铨老师2009年-2013年由国家公派到法国南布列塔尼大学攻读博士学位。博士毕业后,在法国国家信息与自动化研究所从事了两年博士后工作。2015年9月,范老师加入到天津大学,现为天津大学应用数学中心副教授。范老师的主要研究兴趣包括鞅的偏差不等式, Cramer型中偏差, Berry-Esseen估计和自正则化极限理论。主要论文发表在《Stochastic Process. Appl.》,《Bernoulli》,《Electron. J. Probab.》,《Comm. Math. Statist.》,《Sci. China Math.》等杂志上