Optimal Bayesian Minimax Rates for Unconstrained Large Covariance Matrices

被引:10
|
作者
Lee, Kyoungjae [1 ]
Lee, Jaeyong [2 ]
机构
[1] Univ Notre Dame, Dept Appl & Computat Math & Stat, Notre Dame, IN 46556 USA
[2] Seoul Natl Univ, Dept Stat, Seoul, South Korea
来源
BAYESIAN ANALYSIS | 2018年 / 13卷 / 04期
基金
新加坡国家研究基金会;
关键词
Bayesian minimax rate; convergence rate; decision theoretic prior selection; unconstrained covariance; POSTERIOR CONTRACTION; ADAPTIVE ESTIMATION; DISTRIBUTIONS; CONVERGENCE; DIVERGENCES; ENTROPY; MODELS;
D O I
10.1214/18-BA1094
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
We obtain the optimal Bayesian minimax rate for the unconstrained large covariance matrix of multivariate normal sample with mean zero, when both the sample size, n, and the dimension, p, of the covariance matrix tend to infinity. Traditionally the posterior convergence rate is used to compare the frequentist asymptotic performance of priors, but defining the optimality with it is elusive. We propose a new decision theoretic framework for prior selection and define Bayesian minimax rate. Under the proposed framework, we obtain the optimal Bayesian minimax rate for the spectral norm for all rates of p. We also considered Frobenius norm, Bregman divergence and squared log-determinant loss and obtain the optimal Bayesian minimax rate under certain rate conditions on p. A simulation study is conducted to support the theoretical results.
引用
收藏
页码:1211 / 1229
页数:19
相关论文
共 50 条