Metraipolis › archive › dc_dbb17afd492a
On Sequential Entropic Optimal Transport Filter and its Multilevel Variants — arXiv:2611.01752
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01752
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:44:37.595Z
- SHA-256 of the archived text
34e0e9085d94f1b5b196a298a7c129476ff0f40882cab8e077cf62a968a691d6- Stable URL of this page
https://metraipolis.com/documento/dc_dbb17afd492a
How to cite
On Sequential Entropic Optimal Transport Filter and its Multilevel Variants — arXiv:2611.01752 — arXiv (en), https://arxiv.org/abs/2611.01752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbb17afd492a (Metraipolis archive dc_dbb17afd492a, sha256 34e0e9085d94f1b5b196a298a7c129476ff0f40882cab8e077cf62a968a691d6)
BibTeX
@misc{dcdbb17afd492a,
title = {On Sequential Entropic Optimal Transport Filter and its Multilevel Variants — arXiv:2611.01752},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01752},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbb17afd492a; sha256 34e0e9085d94f1b5b196a298a7c129476ff0f40882cab8e077cf62a968a691d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider the problem of filtering partially observed diffusions associated to discrete time observations. This problem requires the development of advanced numerical methods such as particle filters. In this article we develop a new sequential entropic optimal transport filter (EOTF). The main idea is to sample from successive couplings of the filters. To achieve this, we adopt the approach of an entropic optimal transport (EOT) update implemented through a learned Schrödinger potential, in the spirit of the light Schrödinger bridge methodology \cite{korotin2024light}. Based on this, we develop a multilevel version of this filter (ML-EOTF) in which consecutive discretization levels are coupled at the terminal time by a scaled EOT plan with level-dependent regularization $\eps_l=\eps_0 h_l^\kappa$ with discretization stepsize $h_l$. Under mild conditions, we show that the level-difference estimator with exact Schrödinger potentials has variance of order $N_l^{-1}\{h_l^{\beta}+\eps_l\}$, where $\beta$ is the strong-error for the discretized SDE. The analysis is then extended to learned potentials, with all approximation and optimization errors summarized by a joint Kullback--Leibler discrepancy whose contribution to the mean squared error is explicitly quantified. Combined with a fixed-time weak-error estimate, this yields the canonical multilevel complexity $\cO(\delta^{-2}|\log\delta|^2)$ to achieve an MSE of $\delta^2$ for Euler--Maruyama discretizations. Numerical experiments validate the results.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.CO, nuovi lavori del giorno).
Categorie arXiv: Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2611.01752 — 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 2026-11-03T18:14:22.786Z dalla pagina https://arxiv.org/list/stat.CO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).