Bayesian Regularization for Graphical Models with Unequal Shrinkage

05/06/2018
by   Lingrui Gan, et al.
0

We consider a Bayesian framework for estimating a high-dimensional sparse precision matrix, in which adaptive shrinkage and sparsity are induced by a mixture of Laplace priors. Besides discussing our formulation from the Bayesian standpoint, we investigate the MAP (maximum a posteriori) estimator from a penalized likelihood perspective that gives rise to a new non-convex penalty approximating the ℓ_0 penalty. Optimal error rates for estimation consistency in terms of various matrix norms along with selection consistency for sparse structure recovery are shown for the unique MAP estimator under mild conditions. For fast and efficient computation, an EM algorithm is proposed to compute the MAP estimator of the precision matrix and (approximate) posterior probabilities on the edges of the underlying sparse structure. Through extensive simulation studies and a real application to a call center data, we have demonstrated the fine performance of our method compared with existing alternatives.

READ FULL TEXT

page 28

page 29

page 30

page 34

research
06/12/2023

Conditional Matrix Flows for Gaussian Graphical Models

Studying conditional independence structure among many variables with fe...
research
07/26/2019

Bayesian Structure Learning in Graphical Models using Shrinkage priors

We consider the problem of learning the structure of a high dimensional ...
research
04/25/2021

Contraction of a quasi-Bayesian model with shrinkage priors in precision matrix estimation

Currently several Bayesian approaches are available to estimate large sp...
research
04/03/2020

Penalized composite likelihood for colored graphical Gaussian models

This paper proposes a penalized composite likelihood method for model se...
research
09/15/2016

Sparse Tensor Graphical Model: Non-convex Optimization and Statistical Inference

We consider the estimation and inference of sparse graphical models that...
research
04/05/2011

Generalized double Pareto shrinkage

We propose a generalized double Pareto prior for Bayesian shrinkage esti...
research
09/03/2015

Bayesian Masking: Sparse Bayesian Estimation with Weaker Shrinkage Bias

A common strategy for sparse linear regression is to introduce regulariz...

Please sign up or login with your details

Forgot password? Click here to reset