【反问题】系列学术报告（2）
题目: Variational Bayes' approach for functions and applications to some inverse problems
报告人： 贾骏雄, (副教授), 西安交通大学
时间：2020/11/18 周三 15：00-16：00
腾讯会议 ID：900 500 913
会议密码：201118
摘要：Bayesian approach as a useful tool for quantifying uncertainties has been widely used for solving inverse problems of partial differential equations (IPPDE). One of the key difficulties for employing Bayesian approach is how to extra. information from the posterior probability measure. Variational Bayes' method (VBM) is one of the most activate research topics in the field of machine learning, which has the ability to extract posterior information approximately by using much lower computational resources compared with the sampling type method. In this talk, we generalize the usual finite-dimensional VBM to infinite-dimensional space, which makes the usage of VBM for IPPDE rigorously. General infinite-dimensional mean-field approximation theory has been established, and has been applied to abstract linear inverse problems with Gaussian and Laplace noise assumption. Finally, two numerical examples are given which illustrate the effectiveness of the proposed approach.
报告人简介：贾骏雄博士2015年毕业于西安交通大学且于同年留校任教，2017年聘为西安交通大学数学学院副教授，主要研究领域为反问题的贝叶斯推断方法。主持国家自然科学基金青年、面上项目各一项，2017年获得陕西省优秀博士学位论文奖、陕西省数学会优秀论文奖，2018年获西安交通大学第四届十大学术新人奖，2020年入选陕西高校青年杰出人才支持计划。在Inverse Probl., J. Funct. Anal., Inverse Probl. Imag., J. Appl. Geophys., J. Differential Equations等国际著名期刊上共发表论文27篇
