Convergence rates for Bayesian density estimation of infinite-dimensional exponential families

DOI10.1214/009053606000000911zbMATH Open1114.62043arXiv0708.0175OpenAlexW3104787561MaRDI QIDQ2373583FDOQ2373583

Authors: C. Scricciolo 

Publication date: 12 July 2007

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

Abstract: We study the rate of convergence of posterior distributions in density estimation problems for log-densities in periodic Sobolev classes characterized by a smoothness parameter p. The posterior expected density provides a nonparametric estimation procedure attaining the optimal minimax rate of convergence under Hellinger loss if the posterior distribution achieves the optimal rate over certain uniformity classes. A prior on the density class of interest is induced by a prior on the coefficients of the trigonometric series expansion of the log-density. We show that when p is known, the posterior distribution of a Gaussian prior achieves the optimal rate provided the prior variances die off sufficiently rapidly. For a mixture of normal distributions, the mixing weights on the dimension of the exponential family are assumed to be bounded below by an exponentially decreasing sequence. To avoid the use of infinite bases, we develop priors that cut off the series at a sample-size-dependent truncation point. When the degree of smoothness is unknown, a finite mixture of normal priors indexed by the smoothness parameter, which is also assigned a prior, produces the best rate. A rate-adaptive estimator is derived.

Full work available at URL: https://arxiv.org/abs/0708.0175

Recommendations

• Posterior concentration rates for infinite dimensional exponential families
• Adaptive Bayesian density estimation with location-scale mixtures
• Posterior convergence rates of Dirichlet mixtures at smooth densities
• Convergence rates for posterior distributions and adaptive estimation
• On Rates of Convergence for Bayesian Density Estimation

zbMATH Keywords

rate of convergencesieve priorBayesian adaptive density estimationinfinite-dimensional exponential familyposterior distributio

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Bayesian problems; characterization of Bayes procedures (62C10)

Cites Work

• Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities.
• Towards a practicable Bayesian nonparametric density estimator
• Convergence rates of posterior distributions.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Convergence rates for density estimation with Bernstein polynomials.
• On the Bernstein-von Mises theorem with infinite-dimensional parameters
• Bayesian aspects of some nonparametric problems
• Adaptive Bayesian inference on the mean of an infinite-dimensional normal distribution
• Posterior consistency of Dirichlet mixtures in density estimation
• Rates of convergence of posterior distributions.
• Consistency of Bernstein Polynomial Posteriors
• New approaches to Bayesian consistency
• The consistency of posterior distributions in nonparametric problems
• On Bayesian consistency
• Approximation of density functions by sequences of exponential families
• PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
• Information-theoretic determination of minimax rates of convergence
• Convergence rates for posterior distributions and adaptive estimation
• Bayesian goodness-of-fit testing using infinite-dimensional exponential families
• Title not available (Why is that?)
• Estimation of distributions using orthogonal expansions
• Exponential Models, Maximum Likelihood Estimation, and the Haar Condition
• More on Estimation of Distributions Using Orthogonal Expansions
• A Note on Density Estimation Using Orthogonal Expansions

Cited In (28)

• ADAPTIVE BAYESIAN ESTIMATION OF CONDITIONAL DENSITIES
• Rates of Convergence for a Bayesian Level Set Estimation
• On Rates of Convergence for Bayesian Density Estimation
• Rates of contraction with respect to \(L_2\)-distance for Bayesian nonparametric regression
• Convergence rates of nonparametric posterior distributions
• Comparing two populations using Bayesian Fourier series density estimation
• Construction of credible intervals for nonlinear regression models with unknown error distributions
• Bernstein-von Mises theorem for linear functionals of the density
• A Universal Prior Distribution for Bayesian Consistency of Non parametric Procedures
• Anisotropic function estimation using multi-bandwidth Gaussian processes
• Rate exact Bayesian adaptation with modified block priors
• Adaptive Bayesian inference on the mean of an infinite-dimensional normal distribution
• Bayes and maximum likelihood for \(L^1\)-Wasserstein deconvolution of Laplace mixtures
• Oracle posterior contraction rates under hierarchical priors
• Adaptive Bayesian density estimation with location-scale mixtures
• Empirical Bayes scaling of Gaussian priors in the white noise model
• Posterior rates of convergence for Dirichlet mixtures of exponential power densities
• Heavy-tailed Bayesian nonparametric adaptation
• Adaptive Bayesian estimation of conditional discrete-continuous distributions with an application to stock market trading activity
• Quasi-Bayesian analysis of nonparametric instrumental variables models
• Bayesian adaptation
• Bayesian optimal adaptive estimation using a sieve prior
• Bayesian sieve methods: approximation rates and adaptive posterior contraction rates
• Hierarchical Bayesian modeling of marked non-homogeneous Poisson processes with finite mixtures and inclusion of covariate information
• \(L^\infty\) metric criteria for convergence in Bayesian recursive inference systems
• sppmix: Poisson point process modeling using normal mixture models
• Bayesian regression with nonparametric heteroskedasticity
• Adaptive Bayesian Procedures Using Random Series Priors

This page was built for publication: Convergence rates for Bayesian density estimation of infinite-dimensional exponential families

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2373583)