Metraipolis › archive › dc_97fc92354ca2
A probabilistic score estimation using the Bismut--Elworthy--Li formula — arXiv:2611.03915
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03915
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:47:22.625Z
- SHA-256 of the archived text
5e2dbcc4404e6773fa889149b05fa56a32e9b676f9e2cd85abbf9b18d6a4c777- Stable URL of this page
https://metraipolis.com/documento/dc_97fc92354ca2
How to cite
A probabilistic score estimation using the Bismut--Elworthy--Li formula — arXiv:2611.03915 — arXiv (en), https://arxiv.org/abs/2611.03915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97fc92354ca2 (Metraipolis archive dc_97fc92354ca2, sha256 5e2dbcc4404e6773fa889149b05fa56a32e9b676f9e2cd85abbf9b18d6a4c777)
BibTeX
@misc{dc97fc92354ca2,
title = {A probabilistic score estimation using the Bismut--Elworthy--Li formula — arXiv:2611.03915},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03915},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97fc92354ca2; sha256 5e2dbcc4404e6773fa889149b05fa56a32e9b676f9e2cd85abbf9b18d6a4c777},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Score-learning methods generally lack pointwise supervision, which affects the training accuracy, particularly in regions where SDE trajectories are rare. To address this challenge, we introduce a novel method called \emph{BEL anchors}, which uses Monte Carlo score estimates at user-selected space-time query points. By combining a Feynman--Kac representation of the Fokker--Planck equation with the Bismut--Elworthy--Li formula, our estimator requires neither closed-form transition densities, spatial discretization, nor derivatives of the initial density. We derive its asymptotic variance and use the anchors as sparse supervised targets for existing score-learning objectives. Experiments show that BEL anchors improve implicit score matching in poorly sampled regions, prevent score-PINN collapse, and enable accurate sample regeneration in several numerical examples.
Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.PR, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2611.03915 — 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 2026-11-04T12:32:02.027Z dalla pagina https://arxiv.org/list/math.PR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).