Metraipolis › archive › dc_7fe0b001407d

Posterior contraction rates in Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families — arXiv:2608.11130

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11130
License (as archived)
CC0-1.0
Archived
2026-10-19T06:22:49.193Z
SHA-256 of the archived text
7f9cde7704690596d10ae5a1338152a482846f23ef226710f06c9357eabb0e50
Stable URL of this page
https://metraipolis.com/documento/dc_7fe0b001407d

How to cite

Posterior contraction rates in Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families — arXiv:2608.11130 — arXiv (en), https://arxiv.org/abs/2608.11130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fe0b001407d (Metraipolis archive dc_7fe0b001407d, sha256 7f9cde7704690596d10ae5a1338152a482846f23ef226710f06c9357eabb0e50)
BibTeX
@misc{dc7fe0b001407d,
  title = {Posterior contraction rates in Sobolev norms and Bayesian derivative estimation for infinite-dimensional exponential families — arXiv:2608.11130},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11130},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fe0b001407d; sha256 7f9cde7704690596d10ae5a1338152a482846f23ef226710f06c9357eabb0e50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in stat.ML).
Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.11130 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:15:21.795Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).