Adaptive Bernstein-von Mises theorems in Gaussian white noise

DOI10.1214/16-AOS1533MaRDI QIDQ682292zbMATH OpenFDO

Authors Kolyan Ray

Publication date 14 February 2018

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

Full work available at URL https://arxiv.org/abs/1407.3397, https://projecteuclid.org/euclid.aos/1513328581

zbMATH Keywords

adaptationBayesian inferenceconfidence setcredible setposterior asymptotics

Mathematics Subject Classification ID

Bayesian inference (62F15) Nonparametric regression and quantile regression (62G08) Nonparametric tolerance and confidence regions (62G15) Asymptotic properties of nonparametric inference (62G20)

Abstract: We investigate Bernstein-von Mises theorems for adaptive nonparametric Bayesian procedures in the canonical Gaussian white noise model. We consider both a Hilbert space and multiscale setting with applications in $L^2$ and $L^{i}nfty$ respectively. This provides a theoretical justification for plug-in procedures, for example the use of certain credible sets for sufficiently smooth linear functionals. We use this general approach to construct optimal frequentist confidence sets based on the posterior distribution. We also provide simulations to numerically illustrate our approach and obtain a visual representation of the geometries involved.

Review text

The author considers the problem of generating credible sets in the canonical Gaussian white noise model. The construction is based on theoretical results about Bernstein-von Mises theorems for adaptive nonparametric Bayesian procedures. Some applications are considered and some simulations are provided for the illustration of the usefulness of the introduced approach.

Recommendations

• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• On the Bernstein-von Mises phenomenon in the Gaussian white noise model
• Bernstein-von Mises theorems for Gaussian regression with increasing number of regressors
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models

Cited in

(35)

• On the Bernstein-von Mises phenomenon in the Gaussian white noise model
• Multiscale scanning in inverse problems
• Empirical Bayes oracle uncertainty quantification for regression
• Coverage of credible intervals in nonparametric monotone regression
• On the Bernstein-von Mises theorem for the Dirichlet process
• Posterior contraction and credible regions for level sets
• A review of uncertainty quantification for density estimation
• Variable selection consistency of Gaussian process regression
• Statistical guarantees for Bayesian uncertainty quantification in nonlinear inverse problems with Gaussian process priors
• Uncertainty quantification for Bayesian CART
• Spike and slab Pólya tree posterior densities: adaptive inference
• Optional Pólya trees: posterior rates and uncertainty quantification
• Learning the smoothness of noisy curves with application to online curve estimation
• Posterior contraction and credible sets for filaments of regression functions
• Nonparametric statistical inference for drift vector fields of multi-dimensional diffusions
• Asymptotic frequentist coverage properties of Bayesian credible sets for sieve priors
• On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
• Comment: ``Bayes, oracle Bayes and empirical Bayes
• Bernstein-von Mises theorems for statistical inverse problems. II: Compound Poisson processes
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• Frequentist consistency of variational Bayes
• Can we trust Bayesian uncertainty quantification from Gaussian process priors with squared exponential covariance kernel?
• Variational Bayes for High-Dimensional Linear Regression With Sparse Priors
• On adaptive confidence sets for the Wasserstein distances
• On some information-theoretic aspects of non-linear statistical inverse problems
• Bayesian multiscale analysis of the Cox model
• Heavy-tailed Bayesian nonparametric adaptation
• Ideal Bayesian Spatial Adaptation
• On log-concave approximations of high-dimensional posterior measures and stability properties in non-linear inverse problems
• Semiparametric Bernstein-von Mises phenomenon via isotonized posterior in Wicksell's problem
• Projection-posterior for variable selection: weak limit and coverage
• Semi-parametric Bernstein-von Mises theorem in linear inverse problems
• Linear methods for nonlinear inverse problems
• Bernstein-von Mises theorems for statistical inverse problems. I: Schrödinger equation

This page was built for publication: Adaptive Bernstein-von Mises theorems in Gaussian white noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q682292)