报告人：胡文清教授（Missouri University of Science and Technology）

报告题目：A random perturbation approach to some stochastic approximation algorithms in optimization

报告摘要：Many large-scale learning problems in modern statistics and machine learning can be reduced to solving stochastic optimization problems, i.e., the search for (local) minimum points of the expectation of an objective random function (loss function). These optimization problems are usually solved by certain stochastic approximation algorithms, which are recursive update rules with random inputs in each iteration. In this talk, we will be considering various types of such stochastic approximation algorithms, including the stochastic gradient descent, the stochastic composite gradient descent, as well as the stochastic heavy-ball method. By introducing approximating diffusion processes to the discrete recursive schemes, we will analyze the convergence of the diffusion limits to these algorithms via delicate techniques in stochastic analysis and asymptotic methods, in particular random perturbations of dynamical systems. This talk is based on a series of joint works with Chris Junchi Li (Princeton), Weijie Su (UPenn) and Haoyi Xiong (Missouri S&T).

报告人简介：胡文清博士本科毕业于北京大学数学学院，在University of Maryland, College Park(美国)获数学博士学位，曾在University of Minnesota(美国)做博士后，现为 Missouri University of Science and Technology(美国)助理教授。主要研究领域：Stochastic Analysis, Stochastic Dynamical Systems, (Stochastic) Partial Differential Equations。在Communications in Mathematical Physics, Nonlinearity, Communications in Partial Differential Equations, Stochastic Processes and their Applications, Journal of Statistical Physics 等重要期刊发表论文多篇。

报告时间：2018年6月23日（星期六）上午10:30 -11:30

报告地点：科技楼南楼702