一、题目

Stein variational gradient descent with local approximations

二、主讲人

闫亮

三、摘要

Bayesian computation plays an important role in modern machine learning and statistics to reason about uncertainty. A key computational challenge in Bayesian inference is to develop efficient techniques to approximate, or draw samples from posterior distributions. Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for this issue. However, the vanilla SVGD requires calculating the gradient of the target density and cannot be applied when the gradient is unavailable or too expensive to evaluate. In this talk we explore one way to address this challenge by the construction of a local surrogate for the target distribution which the gradient can be obtained in a much more computationally feasible manner. To this end we propose a general adaptation procedure to refine the local approximation online without destroying the convergence of the resulting SVGD. This significantly reduces the computational cost of SVGD and leads to a suite of algorithms that are straightforward to implement. The new algorithm is illustrated on a set of challenging Bayesian inverse problems, and numerical experiments demonstrate a clear improvement in performance and applicability of standard SVGD.

四、主讲人简介

闫亮，东南大学副教授，博士生导师.主要从事不确定性量化、贝叶斯反问题理论与算法的研究。2018年入选东南大学“至善青年学者”（A层次）支持计划，2017年入选江苏省高校“青蓝工程”优秀青年骨干教师培养对象。目前主持国家自然科学基金面上项目一项，主持完成国家自然科学基金青年项目和江苏省自然科学基金青年项目各一项。已在《SIAM J. Sci. Comput.》《Inverse Problems》《J. Comput. Phys.》等国内外刊物上发表20多篇学术论文。

五、邀请人

赵卫东 数学学院教授

六、时间

12月22日（周二）11:00-12:00

七、地点

腾讯会议，ID：585 798 369

https://meeting.tencent.com/s/HMGBsrd6HrFT

八、主办方

山东大学数学学院