Metraipolis › archive › dc_c9213fb06a35
Probabilistic Meshless Methods on Manifolds — arXiv:2610.39855
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39855
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:27:18.341Z
- SHA-256 of the archived text
07a3dfe37f38792185482ead2c097da07de22aa57ce616b390e04ccbfa7d38ce- Stable URL of this page
https://metraipolis.com/documento/dc_c9213fb06a35
How to cite
Probabilistic Meshless Methods on Manifolds — arXiv:2610.39855 — arXiv (en), https://arxiv.org/abs/2610.39855 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9213fb06a35 (Metraipolis archive dc_c9213fb06a35, sha256 07a3dfe37f38792185482ead2c097da07de22aa57ce616b390e04ccbfa7d38ce)
BibTeX
@misc{dcc9213fb06a35,
title = {Probabilistic Meshless Methods on Manifolds — arXiv:2610.39855},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39855},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9213fb06a35; sha256 07a3dfe37f38792185482ead2c097da07de22aa57ce616b390e04ccbfa7d38ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39855. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Probabilistic meshless methods solve partial differential equations (PDEs) by placing a Gaussian process prior on the solution and conditioning it on the PDE at a finite set of collocation nodes. The posterior provides both an approximation of the solution and a Bayesian quantification of its error. While these methods are well established on Euclidean domains, their extension to manifolds lacks, to our knowledge, any convergence analysis. We extend them to compact manifolds and study their convergence in two settings. First, for known manifolds whose Laplace-Beltrami eigenpairs are available, the prior can be evaluated exactly, but the PDE operator generally cannot be applied to it in closed form. We replace this operator by a standard generalized finite difference discretization on a point cloud sampled from the manifold, and show that the resulting method is consistent at the points of the cloud, at a rate governed by their fill distance. Second, for implicit manifolds, known only through a point cloud, both the prior and the operator must be approximated. We propose a new generalized finite difference scheme with a free stencil radius, and show that it retains the consistency of the standard construction while controlling the growth of its coefficients, and that an appropriate radius yields uniform convergence of the discrete Gram matrix. In both settings, we derive error bounds for the posterior mean which separate the collocation error intrinsic to the method from the error due to approximating the operator and, for implicit manifolds, the prior. Experiments on the circle, the sphere and the flat torus confirm our theoretical claims. On real-world cortical thickness data, our approach attains the accuracy of established discretizations, while conditioning on fewer than a tenth of the observations and providing a credible interval at every vertex. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.39855 — 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 2026-11-01T02:12:44.315Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).