通知公告

通知公告

通知公告

当前位置: 首页 - 通知公告 - 正文

特邀福建师范大学王健教授作线上学术报告

发布日期:2020-05-15

点击量:


报告题目:Approximate sampling from heavy-tailed distributions via stable-driven SDEs

报告时间:2020517日(周日)上午08:30—09:20

报告人:王健 教授

报告地点:Zoom云会议(ID838 4831 5631, 密码:nanxinda60

报告摘要:Construction of numerous sampling algorithms is based on the well-known fact that certain Gibbs measures are stationary distributions of ergodic stochastic differential equations driven by the Brownian motion. However, for heavy-tailed distributions it can be shown that the associated SDE is not exponentially ergodic and that related sampling algorithms may perform poorly. A natural idea that has recently been explored in the machine learning literature in this context is to make use of stochastic processes with heavy tails instead of the Brownian motion. In this talk, we provide a rigorous theoretical framework for studying the problem of approximating heavy-tailed distributions via ergodic SDEs driven by symmetric (rotationally invariant) α-stable processes.

欢迎广大师生踊跃参加!

数学与统计学院

2020515

附:专家简介

 

王健,福建师范大学教授,博士生导师,2015年获批国家优秀青年科学基金项目。2001年本科毕业于福建师范大学数学系,同年留校工作;2004年在福建师范大学获得硕士学位;20059月考入北京师范大学,师从中国科学院院士、北京师范大学陈木法教授,20086月获得理学博士学位。2009获得德国洪堡基金,2014年获得日本学术振兴基金,2015年获得国家自然科学基金优秀青年基金,同年也获得霍英东教育基金会高等院校青年教师基金。研究兴趣:随机分析。在《Stochastic Process. Appl.J. Funct. Anal. Trans. Amer. Math. Soc》,《 J. Math. Pures Appl.等国际权威杂志上发表论文80余篇.