SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alberola-Boloix, Enric, Casado-Telletxea, Ioar
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911538921603072
author Alberola-Boloix, Enric
Casado-Telletxea, Ioar
author_facet Alberola-Boloix, Enric
Casado-Telletxea, Ioar
contents We derive posterior contraction rates (PCRs) and finite-sample Bernstein von Mises (BvM) results for non-parametric Bayesian models by extending the diffusion-based framework of Mou et al. (2024) to the infinite-dimensional setting. The posterior is represented as the invariant measure of a Langevin stochastic partial differential equation (SPDE) on a separable Hilbert space, which allows us to control posterior moments and obtain non-asymptotic concentration rates in Hilbert norms under various likelihood curvature and regularity conditions. We also establish a quantitative Laplace approximation for the posterior. The theory is illustrated in a nonparametric linear Gaussian inverse problem.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22468
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
Alberola-Boloix, Enric
Casado-Telletxea, Ioar
Machine Learning
Statistics Theory
We derive posterior contraction rates (PCRs) and finite-sample Bernstein von Mises (BvM) results for non-parametric Bayesian models by extending the diffusion-based framework of Mou et al. (2024) to the infinite-dimensional setting. The posterior is represented as the invariant measure of a Langevin stochastic partial differential equation (SPDE) on a separable Hilbert space, which allows us to control posterior moments and obtain non-asymptotic concentration rates in Hilbert norms under various likelihood curvature and regularity conditions. We also establish a quantitative Laplace approximation for the posterior. The theory is illustrated in a nonparametric linear Gaussian inverse problem.
title SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2603.22468