Besov-Laplace priors in density estimation: optimal posterior contraction rates and adaptation

DOI10.1214/23-EJS2161arXiv2208.14350OpenAlexW4387317067MaRDI QIDQ6184875FDOQ6184875

M. Giordano

Publication date: 5 January 2024

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

Abstract: Besov priors are nonparametric priors that model spatially inhomogeneous functions. They are routinely used in inverse problems and imaging, where they exhibit attractive sparsity-promoting and edge-preserving features. A recent line of work has initiated the study of their asymptotic frequentist convergence properties. In the present paper, we consider the theoretical recovery performance of the posterior distributions associated to Besov-Laplace priors in the density estimation model, under the assumption that the observations are generated by a possibly spatially inhomogeneous true density belonging to a Besov space. We improve on existing results and show that carefully tuned Besov-Laplace priors attain optimal posterior contraction rates. Furthermore, we show that hierarchical procedures involving a hyper-prior on the regularity parameter lead to adaptation to any smoothness level.

Full work available at URL: https://arxiv.org/abs/2208.14350

zbMATH Keywords

frequentist analysis of Bayesian proceduresBayesian nonparametric inferencespatially inhomogeneous functionsLaplace priorBesov prior

Mathematics Subject Classification ID

Bayesian inference (62F15) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Nonlinear total variation based noise removal algorithms
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Fundamentals of Nonparametric Bayesian Inference
• Convergence rates of posterior distributions for non iid observations
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• Discretization-invariant Bayesian inversion and Besov space priors
• Nonparametric Bayesian model selection and averaging
• Bayesian inverse problems with non-conjugate priors
• Non-Gaussian statistical inverse problems. Part I: Posterior distributions
• Can one use total variation prior for edge-preserving Bayesian inversion?
• Bayesian inverse problems with Gaussian priors
• Theory of function spaces
• Wavelets, approximation, and statistical applications
• Lower bounds for posterior rates with Gaussian process priors
• Gaussian process methods for one-dimensional diffusions: optimal rates and adaptation
• Bayes procedures for adaptive inference in inverse problems for the white noise model
• Bayesian optimal adaptive estimation using a sieve prior
• Nonparametric statistical inverse problems
• On universal Bayesian adaptation
• Rates of contraction of posterior distributions based on Gaussian process priors
• Rates of contraction for posterior distributions in \(L^{r}\)-metrics, \(1 \leq r \leq \infty\)
• Besov priors for Bayesian inverse problems
• Rates of contraction of posterior distributions based on \(p\)-exponential priors
• Bayesian approach to inverse problems for functions with a variable-index Besov prior
• On statistical Calderón problems
• Consistency of Bayesian inference with Gaussian process priors in an elliptic inverse problem
• Convergence Rates for Penalized Least Squares Estimators in PDE Constrained Regression Problems
• Nonparametric Bayesian inference for reversible multidimensional diffusions
• Maximuma posterioriprobability estimates in infinite-dimensional Bayesian inverse problems
• A scalable algorithm for MAP estimators in Bayesian inverse problems with Besov priors
• Consistency of Bayesian inference with Gaussian process priors for a parabolic inverse problem
• Sparsity-promoting Bayesian inversion
• Sparsity-promoting and edge-preserving maximum a posteriori estimators in non-parametric Bayesian inverse problems
• Consistent Inversion of Noisy <scp>Non‐Abelian X‐Ray</scp> Transforms
• Bayesian wavelet denoising: Besov priors and non-Gaussian noises.
• Bayesian Inverse Problems with $l_1$ Priors: A Randomize-Then-Optimize Approach
• Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
• Random tree Besov priors -- towards fractal imaging

Cited In (1)

• Heavy-tailed Bayesian nonparametric adaptation

This page was built for publication: Besov-Laplace priors in density estimation: optimal posterior contraction rates and adaptation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6184875)