Metraipolis › archive › dc_049c2e01e6ee

On Prior-to-Posterior Stability in the Wasserstein Metric for Bayesian Inverse Problems — arXiv:2609.07197

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07197
License (as archived)
CC0-1.0
Archived
2026-10-16T14:48:02.817Z
SHA-256 of the archived text
64687ff516766608f93f528b6095e4332de3445de062cd48bd87930a12a87f94
Stable URL of this page
https://metraipolis.com/documento/dc_049c2e01e6ee

How to cite

On Prior-to-Posterior Stability in the Wasserstein Metric for Bayesian Inverse Problems — arXiv:2609.07197 — arXiv (en), https://arxiv.org/abs/2609.07197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_049c2e01e6ee (Metraipolis archive dc_049c2e01e6ee, sha256 64687ff516766608f93f528b6095e4332de3445de062cd48bd87930a12a87f94)
BibTeX
@misc{dc049c2e01e6ee,
  title = {On Prior-to-Posterior Stability in the Wasserstein Metric for Bayesian Inverse Problems — arXiv:2609.07197},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07197},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_049c2e01e6ee; sha256 64687ff516766608f93f528b6095e4332de3445de062cd48bd87930a12a87f94},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Priors in Bayesian inverse problems are often approximated through discretization, hyperparameter estimation, or generative modeling. Understanding how prior approximation errors propagate to the posterior and subsequent predictions is therefore important. In this work, we study the stability of the prior-to-posterior map where both prior and posterior perturbations are measured in the same Wasserstein metric $W_p$, $p\geq1$. We identify verifiable conditions on likelihood regularity and admissible prior classes that ensure uniform, Hölder, and Lipschitz stability. For bounded likelihoods that are uniformly continuous on bounded sets, uniform stability holds over prior classes with uniformly integrable $p$-th moments and a common positive evidence lower bound. With global Hölder regularity of the likelihood and uniform bounds on higher prior moments, a coupling argument leads to a Hölder estimate with a sharp exponent. For $p>1$, a Lipschitz likelihood need not give Lipschitz stability, even for priors with bounded support. We establish Lipschitz stability through an interpolation argument under uniform Poincaré bounds and a globally Lipschitz potential with uniformly bounded essential oscillation under the priors. For Gaussian priors with additive Gaussian noise and bounded Lipschitz forward models, these estimates give posterior $W_2$ bounds even for mutually singular prior perturbations. Numerical experiments for a Darcy inverse problem illustrate the predicted Hölder and Lipschitz rates and the resulting control of errors in the posterior mean and standard deviation of a Lipschitz quantity of interest.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-09 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.07197 — 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 2026-10-16T14:30:08.712Z dalla pagina https://arxiv.org/catchup/math.NA/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).