Global Convergence of EM

发布时间：2021-12-03 作者：77779193永利官网浏览次数：

Speaker:	Zhou Huibin	DateTime:	2021年12月12日（周日）上午10：00-11：00
Brief Introduction to Speaker: Professor Harrison H. Zhou is currently teaching in the Department of STATistics of Yale University, USA. He has been a full professor of the Department of Statistics of Yale University since July 2010, and a head of the department since July 2012. Since 2010, he has also served as the deputy editor-in-chief of Annals of Statistics, one of the four top statistical magazines, and other magazines, such as Bernoulli, Journal of Nonparametric Statistics, Stat, etc.		Place:	6号楼415 & ZOOM ID：952 7946 3736
Abstract: In this talk I will first review a recent joint work with Yihong Wu. It showed that the randomly initialized EM algorithm for parameter estimation in the symmetric two-component Gaussian mixtures converges to the MLE in at most n2 iterations with high probability. The work has its limitation: the key “leave-one-coordinate- out” analysis technique there cannot be easily extended to general Gaussian mixtures. In the second part of the talk, I will consider an extension to general Gaussian mixtures by overparameterization, but the progress is still quite preliminary so far