Asymptotically minimax empirical Bayes estimation of a sparse normal mean vector

DOI10.1214/14-EJS949zbMATH Open1302.62015arXiv1304.7366MaRDI QIDQ470502FDOQ470502

Authors: Stephen G. Walker, Ryan Martin 

Publication date: 12 November 2014

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: For the important classical problem of inference on a sparse high-dimensional normal mean vector, we propose a novel empirical Bayes model that admits a posterior distribution with desirable properties under mild conditions. In particular, our empirical Bayes posterior distribution concentrates on balls, centered at the true mean vector, with squared radius proportional to the minimax rate, and its posterior mean is an asymptotically minimax estimator. We also show that, asymptotically, the support of our empirical Bayes posterior has roughly the same effective dimension as the true sparse mean vector. Simulation from our empirical Bayes posterior is straightforward, and our numerical results demonstrate the quality of our method compared to others having similar large-sample properties.

Full work available at URL: https://arxiv.org/abs/1304.7366

Recommendations

• On minimax estimation of a sparse normal mean vector
• Empirical Bayes minimax estimators of matrix normal means
• Empirical Bayes estimators for high-dimensional sparse vectors
• scientific article; zbMATH DE number 524360
• On minimax optimality of sparse Bayes predictive density estimates
• scientific article; zbMATH DE number 571969

zbMATH Keywords

shrinkageposterior concentrationhigh-dimensionaldata-dependent priorfractional likelihoodtwo-groups model

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Empirical decision procedures; empirical Bayes procedures (62C12) Minimax procedures in statistical decision theory (62C20)

Cites Work

• Empirical Bayes posterior concentration in sparse high-dimensional linear models
• Title not available (Why is that?)
• The horseshoe estimator for sparse signals
• The Bayesian Lasso
• Model Selection and Estimation in Regression with Grouped Variables
• Sparsistency and rates of convergence in large covariance matrix estimation
• Needles and straw in haystacks: Empirical Bayes estimates of possibly sparse sequences
• General maximum likelihood empirical Bayes estimation of normal means
• Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means
• Adapting to unknown sparsity by controlling the false discovery rate
• Empirical Bayes selection of wavelet thresholds
• A Selective Overview of Variable Selection in High Dimensional Feature Space (Invited Review Article)
• Convex Optimization, Shape Constraints, Compound Decisions, and Empirical Bayes Rules
• Estimating the Null and the Proportion of Nonnull Effects in Large-Scale Multiple Comparisons
• Convergence rates of posterior distributions.
• Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
• An exploration of aspects of Bayesian multiple testing
• Posterior contraction in sparse Bayesian factor models for massive covariance matrices
• Title not available (Why is that?)
• Optimal rates of convergence for sparse covariance matrix estimation
• Microarrays, empirical Bayes and the two-groups model
• Optimal rates of convergence for covariance matrix estimation
• Oracle convergence rate of posterior under projection prior and Bayesian model selection
• Asymptotic Bayes-optimality under sparsity of some multiple testing procedures
• Optimal rates of convergence for estimating the null density and proportion of nonnull effects in large-scale multiple testing
• Posterior consistency of Dirichlet mixtures in density estimation
• Rates of convergence of posterior distributions.
• Gibbs posterior for variable selection in high-dimensional classification and data mining
• Needles and straw in a haystack: posterior concentration for possibly sparse sequences
• The consistency of posterior distributions in nonparametric problems
• On Bayesian consistency
• On Bayes procedures
• Estimation of a sparse group of sparse vectors
• A nonparametric empirical Bayes framework for large-scale multiple testing
• From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
• Minimax and adaptive inference in nonparametric function estimation

Cited In (36)

• Optimal convergence rates of Bayesian wavelet estimation with a novel empirical prior in nonparametric regression model
• Bayesian fractional posteriors
• A Regression Modeling Approach to Structured Shrinkage Estimation
• Needles and straw in a haystack: robust confidence for possibly sparse sequences
• Spike and slab empirical Bayes sparse credible sets
• The horseshoe estimator: posterior concentration around nearly black vectors
• Conditions for posterior contraction in the sparse normal means problem
• Robust oracle estimation and uncertainty quantification for possibly sparse quantiles
• Bayesian estimation of sparse signals with a continuous spike-and-slab prior
• On optimality of Bayesian testimation in the normal means problem
• The spike-and-slab LASSO
• Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means
• Bayesian linear regression with sparse priors
• Empirical Bayes inference in sparse high-dimensional generalized linear models
• Bayesian inference in high-dimensional linear models using an empirical correlation-adaptive prior
• Bayesian joint inference for multiple directed acyclic graphs
• Empirical Bayes estimators for high-dimensional sparse vectors
• Estimating the mean of high valued observations in high dimensions
• Simultaneous estimation of normal means with side information
• Asymptotic optimality of one-group shrinkage priors in sparse high-dimensional problems
• Estimation of a sparse group of sparse vectors
• Minimax posterior convergence rates and model selection consistency in high-dimensional DAG models based on sparse Cholesky factors
• Empirical Bayes posterior concentration in sparse high-dimensional linear models
• Empirical priors and posterior concentration rates for a monotone density
• Empirical Bayes predictive densities for high-dimensional normal models
• Empirical priors and coverage of posterior credible sets in a sparse normal mean model
• False confidence, non-additive beliefs, and valid statistical inference
• Empirical priors and posterior concentration in a piecewise polynomial sequence model
• A paradoxical argument about domination
• Empirical Bayes analysis of spike and slab posterior distributions
• Scalable Bayesian high-dimensional local dependence learning
• Fast exact Bayesian inference for sparse signals in the normal sequence model
• Empirical priors for prediction in sparse high-dimensional linear regression
• Data-driven priors and their posterior concentration rates
• Prediction risk for the horseshoe regression
• Local posterior concentration rate for multilevel sparse sequences

Uses Software

• EBayesThresh

This page was built for publication: Asymptotically minimax empirical Bayes estimation of a sparse normal mean vector

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q470502)