Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
From MaRDI portal
Publication:1731759
DOI10.1214/18-AOS1689zbMATH Open1417.62140arXiv1611.01205OpenAlexW2963846915MaRDI QIDQ1731759FDOQ1731759
Authors: Xuan Cao, Kshitij Khare, Malay Ghosh 
Publication date: 14 March 2019
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: Covariance estimation and selection for high-dimensional multivariate datasets is a fundamental problem in modern statistics. Gaussian directed acyclic graph (DAG) models are a popular class of models used for this purpose. Gaussian DAG models introduce sparsity in the Cholesky factor of the inverse covariance matrix, and the sparsity pattern in turn corresponds to specific conditional independence assumptions on the underlying variables. A variety of priors have been developed in recent years for Bayesian inference in DAG models, yet crucial convergence and sparsity selection properties for these models have not been thoroughly investigated. Most of these priors are adaptations or generalizations of the Wishart distribution in the DAG context. In this paper, we consider a flexible and general class of these 'DAG-Wishart' priors with multiple shape parameters. Under mild regularity assumptions, we establish strong graph selection consistency and establish posterior convergence rates for estimation when the number of variables p is allowed to grow at an appropriate sub-exponential rate with the sample size n.
Full work available at URL: https://arxiv.org/abs/1611.01205
Recommendations
- Consistent Bayesian sparsity selection for high-dimensional Gaussian DAG models with multiplicative and beta-mixture priors
- Minimax posterior convergence rates and model selection consistency in high-dimensional DAG models based on sparse Cholesky factors
- Compatible priors for model selection of high-dimensional Gaussian DAGs
- Joint Bayesian Variable and DAG Selection Consistency for High-dimensional Regression Models with Network-structured Covariates
- High-dimensional covariance estimation based on Gaussian graphical models
covariance estimationhigh-dimensional dataposterior consistencyBayesian DAG modelsgraph selectionhigh-dimensional multivariate datasets
Asymptotic properties of parametric estimators (62F12) Bayesian inference (62F15) Estimation in multivariate analysis (62H12)
Cites Work
- Parameter priors for directed acyclic graphical models and the characterization of several probability distributions
- A new approach to Cholesky-based covariance regularization in high dimensions
- High dimensional sparse covariance estimation via directed acyclic graphs
- Regularized estimation of large covariance matrices
- \(\ell_{0}\)-penalized maximum likelihood for sparse directed acyclic graphs
- Parsimonious Covariance Matrix Estimation for Longitudinal Data
- Hanson-Wright inequality and sub-Gaussian concentration
- Penalized likelihood methods for estimation of sparse high-dimensional directed acyclic graphs
- Probabilistic graphical models.
- Learning local dependence in ordered data
- Bayesian variable selection with shrinking and diffusing priors
- Bayesian model selection in high-dimensional settings
- Spectrum estimation for large dimensional covariance matrices using random matrix theory
- Schur products and matrix completions
- Wishart distributions for decomposable graphs
- Cholesky Decompositions and Estimation of A Covariance Matrix: Orthogonality of Variance Correlation Parameters
- Covariance matrix selection and estimation via penalised normal likelihood
- On the use of Non-Local Prior Densities in Bayesian Hypothesis Tests
- Posterior convergence rates for estimating large precision matrices using graphical models
- High dimensional posterior convergence rates for decomposable graphical models
- Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
- Objective Bayesian search of Gaussian directed acyclic graphical models for ordered variables with non-local priors
- Objective Bayes Covariate‐Adjusted Sparse Graphical Model Selection
- Bayesian structure learning in graphical models
Cited In (41)
- A new approach for ultrahigh dimensional precision matrix estimation
- Strong selection consistency of Bayesian vector autoregressive models based on a pseudo-likelihood approach
- A permutation-based Bayesian approach for inverse covariance estimation
- Complexity analysis of Bayesian learning of high-dimensional DAG models and their equivalence classes
- Bayesian graph selection consistency under model misspecification
- Compatible priors for model selection of high-dimensional Gaussian DAGs
- Objective Bayes model selection of Gaussian interventional essential graphs for the identification of signaling pathways
- Bayesian adaptive Lasso estimation of large graphical model based on modified Cholesky decomposition
- Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
- Joint Bayesian Variable and DAG Selection Consistency for High-dimensional Regression Models with Network-structured Covariates
- Discussion to: Bayesian graphical models for modern biological applications by Y. Ni, V. Baladandayuthapani, M. Vannucci and F.C. Stingo
- On the non-local priors for sparsity selection in high-dimensional Gaussian DAG models
- Consistent Bayesian sparsity selection for high-dimensional Gaussian DAG models with multiplicative and beta-mixture priors
- Bayesian joint inference for multiple directed acyclic graphs
- Estimating large precision matrices via modified Cholesky decomposition
- A generalized likelihood-based Bayesian approach for scalable joint regression and covariance selection in high dimensions
- A Bayesian Subset Specific Approach to Joint Selection of Multiple Graphical Models
- Consistent skinny Gibbs in probit regression
- Bayesian inference for high-dimensional decomposable graphs
- Bayesian causal inference in probit graphical models
- Network Structure Learning Under Uncertain Interventions
- Bayesian graphical modeling for heterogeneous causal effects
- Spectral Clustering, Bayesian Spanning Forest, and Forest Process
- Bayesian Model Selection of Gaussian Directed Acyclic Graph Structures
- Minimax posterior convergence rates and model selection consistency in high-dimensional DAG models based on sparse Cholesky factors
- A Gibbs sampler for learning DAG: a unification for discrete and Gaussian domains
- High dimensional posterior convergence rates for decomposable graphical models
- A Bayesian approach for learning Bayesian network structures
- Estimation of Gaussian directed acyclic graphs using partial ordering information with applications to DREAM3 networks and dairy cattle data
- A review of Gaussian Markov models for conditional independence
- Bayesian robust learning in chain graph models for integrative pharmacogenomics
- Densely connected sub-Gaussian linear structural equation model learning via \(\ell_1\)- and \(\ell_2\)-regularized regressions
- Joint variable selection and network modeling for detecting eQTLs
- Bayesian bandwidth test and selection for high-dimensional banded precision matrices
- High-dimensional posterior consistency for hierarchical non-local priors in regression
- Gaussian Bayesian network comparisons with graph ordering unknown
- Scalable Bayesian high-dimensional local dependence learning
- Development of network-guided transcriptomic risk score for disease prediction
- Consistent group selection using nonlocal priors in regression
- Bayesian inference of causal effects from observational data in Gaussian graphical models
- Bayesian group selection in logistic regression with application to MRI data analysis
This page was built for publication: Posterior graph selection and estimation consistency for high-dimensional Bayesian DAG models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1731759)
