Metraipolis › archive › dc_626e34ff7f96
Bernstein--von Mises theorems for Bayesian probabilistic numerics — arXiv:2609.04124
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04124
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:30:59.100Z
- SHA-256 of the archived text
c19f034df812081ba7dfde89a0cb5bd8c9f7c666d033fc08936085e60cb44c76- Stable URL of this page
https://metraipolis.com/documento/dc_626e34ff7f96
How to cite
Bernstein--von Mises theorems for Bayesian probabilistic numerics — arXiv:2609.04124 — arXiv (en), https://arxiv.org/abs/2609.04124 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_626e34ff7f96 (Metraipolis archive dc_626e34ff7f96, sha256 c19f034df812081ba7dfde89a0cb5bd8c9f7c666d033fc08936085e60cb44c76)
BibTeX
@misc{dc626e34ff7f96,
title = {Bernstein--von Mises theorems for Bayesian probabilistic numerics — arXiv:2609.04124},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04124},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_626e34ff7f96; sha256 c19f034df812081ba7dfde89a0cb5bd8c9f7c666d033fc08936085e60cb44c76},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04124. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study probabilistic numerical methods for solving nonlinear PDEs from a Bayesian nonparametric perspective. Given noisy evaluations at random collocation points, we place a truncated Gaussian series prior on the unknown solution and establish contraction at the minimax nonparametric rate, up to a logarithmic factor. Our main results give Gaussian approximations of the posterior in positive-order Sobolev spaces and, under suitable conditions, in the uniform topology. This contrasts with classical ill-posed inverse problems, where Bernstein--von Mises theorems typically require substantially weaker topologies. Here, the observation operator is differential rather than smoothing, and inversion of its linearisation gains regularity, making these strong-topology results possible. The posterior may be centred at either the posterior mean or the posterior mode. We further prove that the Gaussian Laplace approximation is asymptotically equivalent to the true posterior at a $\sqrt{N}$-scale.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-04 in math.ST).
Categorie arXiv: Statistics Theory (math.ST) ; Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.04124 — 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 2026-10-17T02:08:32.306Z dalla pagina https://arxiv.org/catchup/math.ST/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).