On Bayesian supremum norm contraction rates

Abstract

Building on ideas from Castillo and Nickl [Ann. Statist. 41 (2013) 1999-2028], a method is provided to study nonparametric Bayesian posterior convergence rates when "strong" measures of distances, such as the sup-norm, are considered. In particular, we show that likelihood methods can achieve optimal minimax sup-norm rates in density estimation on the unit interval. The introduced methodology is used to prove that commonly used families of prior distributions on densities, namely log-density priors and dyadic random density histograms, can indeed achieve optimal sup-norm rates of convergence. New results are also derived in the Gaussian white noise model as a further illustration of the presented techniques.

Published in at http://dx.doi.org/10.1214/14-AOS1253 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (11)

• Rates of contraction of posterior distributions based on Gaussian process priors
• Convergence rates of posterior distributions for noniid observations
• Reproducing kernel Hilbert spaces of Gaussian priors
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• Posterior convergence rates of Dirichlet mixtures at smooth densities
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• Rates of contraction for posterior distributions in $\bolds{L^r}$-metrics, $\bolds{1\le r\le\infty}$
• Lower bounds for posterior rates with Gaussian process priors
• On adaptive posterior concentration rates
• Convergence rates for Bayesian density estimation of infinite-dimensional exponential families
• Adaptive Bayesian density estimation using Pitman-Yor or normalized inverse-Gaussian process kernel mixtures

Cited by in corpus (26)

• Frequentist Consistency of Variational Bayes
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models
• Adaptive Bernstein-von Mises theorems in Gaussian white noise
• Supremum Norm Posterior Contraction and Credible Sets for Nonparametric Multivariate Regression
• Nonparametric statistical inference for drift vector fields of multi-dimensional diffusions
• Frequentist coverage and sup-norm convergence rate in Gaussian process regression
• Bernstein -- von Mises theorems for statistical inverse problems II: Compound Poisson processes
• Bayes factor consistency
• Adaptive Supremum Norm Posterior Contraction: Wavelet Spike-and-Slab and Anisotropic Besov Spaces
• Comparing and weighting imperfect models using D-probabilities
• Convergence Rates of Variational Posterior Distributions
• On the Bernstein-von Mises theorem for the Dirichlet process
• Criteria for posterior consistency
• On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
• Kriging prediction with isotropic Matérn correlations: Robustness and experimental design
• Oracle posterior contraction rates under hierarchical priors
• Covariate-Assisted Bayesian Graph Learning for Heterogeneous Data
• Semiparametric inference using fractional posteriors
• Equivalence of Convergence Rates of Posterior Distributions and Bayes Estimators for Functions and Nonparametric Functionals
• Posterior Contraction and Credible Sets for Filaments of Regression Functions
• Discussion of "Frequentist coverage of adaptive nonparametric Bayesian credible sets"
• Gaussian Approximation of General Nonparametric Posterior Distributions
• Spike and Slab Pólya tree posterior distributions: adaptive inference
• Bayesian Bandwidth Test and Selection for High-dimensional Banded Precision Matrices
• Sharp sup-norm Bayesian curve estimation