Nearly optimal Bayesian shrinkage for high-dimensional regression  

作　　者：Qifan Song Faming Liang 

机构地区：[1]Department of Statistics,Purdue University,West Lafayette,IN 47906,USA

出　　处：《Science China Mathematics》2023年第2期409-442,共34页中国科学：数学（英文版）

基　　金：supported by National Science Foundation of USA(Grant No.DMS1811812);supported by National Science Foundation of USA(Grant No.DMS-2015498);National Institutes of Health of USA(Grant Nos.R01GM117597 and R01GM126089)。

摘　　要：During the past decade,shrinkage priors have received much attention in Bayesian analysis of high-dimensional data.This paper establishes the posterior consistency for high-dimensional linear regression with a class of shrinkage priors,which has a heavy and flat tail and allocates a sufficiently large probability mass in a very small neighborhood of zero.While enjoying its efficiency in posterior simulations,the shrinkage prior can lead to a nearly optimal posterior contraction rate and the variable selection consistency as the spike-and-slab prior.Our numerical results show that under the posterior consistency,Bayesian methods can yield much better results in variable selection than the regularization methods such as LASSO and SCAD.This paper also establishes a BvM-type result,which leads to a convenient way of uncertainty quantification for regression coefficient estimates.

关 键 词：Bayesian variable selection absolutely continuous shrinkage prior heavy tail posterior consistency high-dimensional inference 

分 类 号：O212[理学—概率论与数理统计]