A generalized likelihood-based Bayesian approach for scalable joint regression and covariance selection in high dimensions
From MaRDI portal
Publication:2152553
Abstract: The paper addresses joint sparsity selection in the regression coefficient matrix and the error precision (inverse covariance) matrix for high-dimensional multivariate regression models in the Bayesian paradigm. The selected sparsity patterns are crucial to help understand the network of relationships between the predictor and response variables, as well as the conditional relationships among the latter. While Bayesian methods have the advantage of providing natural uncertainty quantification through posterior inclusion probabilities and credible intervals, current Bayesian approaches either restrict to specific sub-classes of sparsity patterns and/or are not scalable to settings with hundreds of responses and predictors. Bayesian approaches which only focus on estimating the posterior mode are scalable, but do not generate samples from the posterior distribution for uncertainty quantification. Using a bi-convex regression based generalized likelihood and spike-and-slab priors, we develop an algorithm called Joint Regression Network Selector (JRNS) for joint regression and covariance selection which (a) can accommodate general sparsity patterns, (b) provides posterior samples for uncertainty quantification, and (c) is scalable and orders of magnitude faster than the state-of-the-art Bayesian approaches providing uncertainty quantification. We demonstrate the statistical and computational efficacy of the proposed approach on synthetic data and through the analysis of selected cancer data sets. We also establish high-dimensional posterior consistency for one of the developed algorithms.
Recommendations
- Joint Bayesian Variable and DAG Selection Consistency for High-dimensional Regression Models with Network-structured Covariates
- Joint high-dimensional Bayesian variable and covariance selection with an application to eQTL analysis
- Bayesian linear regression for multivariate responses under group sparsity
- Bayesian sparse reduced rank multivariate regression
- Bayesian sparse multiple regression for simultaneous rank reduction and variable selection
Cites work
- A General Framework for Updating Belief Distributions
- A convex pseudolikelihood framework for high dimensional partial correlation estimation with convergence guarantees
- Bayesian graphical Lasso models and efficient posterior computation
- Bayesian variable selection with shrinking and diffusing priors
- Covariate-adjusted precision matrix estimation with an application in genetical genomics
- Estimation of high-dimensional graphical models using regularized score matching
- High-dimensional graphs and variable selection with the Lasso
- Joint high-dimensional Bayesian variable and covariance selection with an application to eQTL analysis
- Joint mean-covariance estimation via the horseshoe
- Joint structural estimation of multiple graphical models
- Multivariate Bayesian Variable Selection and Prediction
- Objective Bayes Covariate‐Adjusted Sparse Graphical Model Selection
- On asymptotically optimal confidence regions and tests for high-dimensional models
- Optimal predictive model selection.
- Partial Gaussian Graphical Model Estimation
- Partial correlation estimation by joint sparse regression models
- Penalized maximum likelihood estimation of multi-layered Gaussian graphical models
- Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
- Simultaneous Variable and Covariance Selection With the Multivariate Spike-and-Slab LASSO
- Simultaneous multiple response regression and inverse covariance matrix estimation via penalized Gaussian maximum likelihood
- Sparse inverse covariance estimation with the graphical lasso
Cited in
(7)- Consistent and scalable Bayesian joint variable and graph selection for disease diagnosis leveraging functional brain network
- Joint Bayesian Variable and DAG Selection Consistency for High-dimensional Regression Models with Network-structured Covariates
- Sparse inference of the human haematopoietic system from heterogeneous and partially observed genomic data
- Covariate-Assisted Bayesian Graph Learning for Heterogeneous Data
- Joint high-dimensional Bayesian variable and covariance selection with an application to eQTL analysis
- Sparse Bayesian additive nonparametric regression with application to health effects of pesticides mixtures
- Bayesian variable selection for matrix autoregressive models
This page was built for publication: A generalized likelihood-based Bayesian approach for scalable joint regression and covariance selection in high dimensions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2152553)
