GEOMETRY OF MAXIMUM LIKELIHOOD ESTIMATION IN GAUSSIAN GRAPHICAL MODELS

被引:39
|
作者
Uhler, Caroline [1 ]
机构
[1] IST Austria, A-3400 Klosterneuburg, Austria
来源
ANNALS OF STATISTICS | 2012年 / 40卷 / 01期
关键词
Gaussian graphical model; maximum likelihood estimation; matrix completion problems; duality; algebraic statistics; algebraic variety; number of observations; sufficient statistics; treewidth; elimination ideal; ML degree; bipartite graphs;
D O I
10.1214/11-AOS957
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We study maximum likelihood estimation in Gaussian graphical models from a geometric point of view. An algebraic elimination criterion allows us to find exact lower bounds on the number of observations needed to ensure that the maximum likelihood estimator (MLE) exists with probability one. This is applied to bipartite graphs, grids and colored graphs. We also study the ML degree, and we present the first instance of a graph for which the MLE exists with probability one, even when the number of observations equals the treewidth.
引用
收藏
页码:238 / 261
页数:24
相关论文
共 50 条