Posterior contraction rates in Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families
Abstract
We study posterior contraction in positive-order Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families. We embed the natural parameter in a Hilbert scale and model it via a Gaussian series prior expanded in the eigenbasis generating the scale. Under a two-sided link condition on the Fisher information and suitable local regularity assumptions, we show that smoothness-matching priors achieve minimax-optimal posterior contraction rates in any Hilbert scale norm up to the regularity of the ground truth. Our analysis builds on the novel approach to posterior contraction based on the Wasserstein distance recently introduced by Dolera et al. (2024, Probab. Theory Relat. Fields). It combines Laplace-type approximations for infinite-dimensional integrals associated to the posterior kernels with a mixed-geometry estimate controlling their stability under fluctuations in the data, itself resting on a tailored Poincaré inequality for posterior distributions conditioned on neighbourhoods of the truth. We apply the general theory to density estimation under the logistic parametrisation, Poisson intensity estimation under the exponential link, and mildly ill-posed linear inverse problems observed in Gaussian white noise. The resulting minimax rates yield optimal recovery of density score functions, derivatives of Poisson intensities and, in a concrete elliptic inverse problem, the unknown source function.
Related
- Sieve-free ReLU Bayesian priors with near-minimax posterior contraction
- Dirichlet Process Mixtures of Trees with Gaussian Process Splits: A Bayesian Nonparametric Framework with Posterior Contraction Rate
- Exponential Contraction for Underdamped Langevin Diffusions with Superlinear Forces
- Conservative neural posterior estimation via distributionally robust training
- A New Extended Exponential Rayleigh Distribution: Estimation and Application
BibTeX
@misc{dolera2026posterior,
title = {{Posterior contraction rates in Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families}},
author = {Emanuele Dolera and Stefano Favaro and Matteo Giordano},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.11130},
eprint = {2608.11130},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.11130},
}
RIS
TY - UNPB
TI - Posterior contraction rates in Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families
AU - Emanuele Dolera
AU - Stefano Favaro
AU - Matteo Giordano
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2608.11130
UR - https://arxiv.org/abs/2608.11130
AB - We study posterior contraction in positive-order Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families. We embed the natural parameter in a Hilbert scale and model it via a Gaussian series prior expanded in the eigenbasis generating the scale. Under a two-sided link condition on the Fisher information and suitable local regularity assumptions, we show that smoothness-matching priors achieve minimax-optimal posterior contraction rates in any Hilbert scale norm up to the regularity of the ground truth. Our analysis builds on the novel approach to posterior contraction based on the Wasserstein distance recently introduced by Dolera et al. (2024, Probab. Theory Relat. Fields). It combines Laplace-type approximations for infinite-dimensional integrals associated to the posterior kernels with a mixed-geometry estimate controlling their stability under fluctuations in the data, itself resting on a tailored Poincaré inequality for posterior distributions conditioned on neighbourhoods of the truth. We apply the general theory to density estimation under the logistic parametrisation, Poisson intensity estimation under the exponential link, and mildly ill-posed linear inverse problems observed in Gaussian white noise. The resulting minimax rates yield optimal recovery of density score functions, derivatives of Poisson intensities and, in a concrete elliptic inverse problem, the unknown source function.
ER -