Asymptotic frequentist coverage properties of Bayesian credible sets for sieve priors

DOI10.1214/19-AOS1881zbMATH Open1471.62350arXiv1609.05067MaRDI QIDQ2215729FDOQ2215729

Authors: Judith Rousseau, Botond Szabó 

Publication date: 14 December 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We investigate the frequentist coverage properties of Bayesian credible sets in a general, adaptive, nonparametric framework. It is well known that the construction of adaptive and honest confidence sets is not possible in general. To overcome this problem we introduce an extra assumption on the functional parameters, the so called "general polished tail" condition. We then show that under standard assumptions both the hierarchical and empirical Bayes methods results in honest confidence sets for sieve type of priors in general settings and we characterize their size. We apply the derived abstract results to various examples, including the nonparametric regression model, density estimation using exponential families of priors, density estimation using histogram priors and nonparametric classification model, for which we show that their size is near minimax adaptive with respect to the considered specific semi-metrics.

Full work available at URL: https://arxiv.org/abs/1609.05067

Recommendations

• Frequentist coverage of adaptive nonparametric Bayesian credible sets
• On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
• Honest Bayesian confidence sets for the \(L^2\)-norm
• Spike and slab empirical Bayes sparse credible sets
• Empirical priors and coverage of posterior credible sets in a sparse normal mean model

zbMATH Keywords

classificationdensity estimationnonparametric regressionadaptationuncertainty quantificationempirical Bayeshierarchical Bayescoveragesieve priorposterior contraction rates

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Density estimation (62G07) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Nonparametric tolerance and confidence regions (62G15)

Cites Work

• Confidence bands in density estimation
• Asymptotic Statistics
• Confidence sets in sparse regression
• Mathematical foundations of infinite-dimensional statistical models
• Introduction to nonparametric estimation
• Convergence rates of posterior distributions for non iid observations
• Convergence rates of posterior distributions.
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• Anti-concentration and honest, adaptive confidence bands
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models
• On signal detection and confidence sets for low rank inference problems
• On the Bernstein-von Mises theorem with infinite-dimensional parameters
• Asymptotic behaviour of the empirical Bayes posteriors associated to maximum marginal likelihood estimator
• Bayesian inverse problems with Gaussian priors
• An analysis of Bayesian inference for nonparametric regression
• Lower bounds for posterior rates with Gaussian process priors
• Frequentist coverage of adaptive nonparametric Bayesian credible sets
• Bayesian optimal adaptive estimation using a sieve prior
• Bayes and empirical Bayes: do they merge?
• Bernstein-von Mises theorem for linear functionals of the density
• Rates of contraction of posterior distributions based on Gaussian process priors
• On the Bernstein-von Mises phenomenon in the Gaussian white noise model
• Title not available (Why is that?)
• Bayesian goodness of fit testing with mixtures of triangular distributions
• On adaptive posterior concentration rates
• Minimax nonparametric classification. II. Model selection for adaptation
• Minimax nonparametric classification .I. Rates of convergence
• Adaptive empirical Bayesian smoothing splines
• Supremum norm posterior contraction and credible sets for nonparametric multivariate regression
• Random vectors in the isotropic position
• An adaptation theory for nonparametric confidence intervals
• Adaptive nonparametric confidence sets
• Adaptive confidence bands for Markov chains and diffusions: estimating the invariant measure and the drift
• On nonparametric confidence intervals
• Adaptive confidence interval for pointwise curve estimation.
• Honest adaptive confidence bands and self-similar functions
• A sharp adaptive confidence ball for self-similar functions
• Adaptive confidence sets in \(L^2\)
• Honest and adaptive confidence sets in \(L_p\)
• On adaptive inference and confidence bands
• Estimating a smooth function on a large graph by Bayesian Laplacian regularisation
• Bayesian goodness-of-fit testing using infinite-dimensional exponential families
• Posterior concentration rates for infinite dimensional exponential families
• On Rates of Convergence for Bayesian Density Estimation
• Adaptive Bernstein-von Mises theorems in Gaussian white noise
• Adaptive Bayesian credible sets in regression with a Gaussian process prior
• Uncertainty quantification for the horseshoe (with discussion)
• On coverage and local radial rates of credible sets
• Empirical Bayes analysis of spike and slab posterior distributions
• Spike and slab empirical Bayes sparse credible sets
• Needles and straw in a haystack: robust confidence for possibly sparse sequences
• Optimal adaptive inference in random design binary regression
• Rate exact Bayesian adaptation with modified block priors

Cited In (19)

• Frequency coverage properties of a uniform shrinkage prior distribution
• Needles and straw in a haystack: robust confidence for possibly sparse sequences
• Spike and slab empirical Bayes sparse credible sets
• On adaptive confidence sets for the Wasserstein distances
• On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
• On coverage and local radial rates of credible sets
• Frequentist validity of Bayesian limits
• Joint non-parametric estimation of mean and auto-covariances for Gaussian processes
• Uncertainty quantification for sparse spectral variational approximations in Gaussian process regression
• Oracle posterior contraction rates under hierarchical priors
• Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel?
• Coverage properties of one-sided intervals in the discrete case and application to matching priors
• A review of uncertainty quantification for density estimation
• Frequentist coverage of adaptive nonparametric Bayesian credible sets
• Empirical priors and coverage of posterior credible sets in a sparse normal mean model
• Discussion of ``Frequentist coverage of adaptive nonparametric Bayesian credible sets
• Distributed function estimation: adaptation using minimal communication
• On a better lower bound for the frequentist probability of coverage of Bayesian credible intervals in restricted parameter spaces
• Title not available (Why is that?)

This page was built for publication: Asymptotic frequentist coverage properties of Bayesian credible sets for sieve priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215729)