Metraipolis › archive › dc_98403cd24237
Sieve Estimation of Optimal Transport Maps from Paired Data in Gaussian Spaces — arXiv:2609.09089
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09089
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T14:10:03.600Z
- SHA-256 of the archived text
590c093d7abfea0c3e58797033401f5914c20498c4676c26f3548990ffdb4c19- Stable URL of this page
https://metraipolis.com/documento/dc_98403cd24237
How to cite
Sieve Estimation of Optimal Transport Maps from Paired Data in Gaussian Spaces — arXiv:2609.09089 — arXiv (en), https://arxiv.org/abs/2609.09089 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98403cd24237 (Metraipolis archive dc_98403cd24237, sha256 590c093d7abfea0c3e58797033401f5914c20498c4676c26f3548990ffdb4c19)
BibTeX
@misc{dc98403cd24237,
title = {Sieve Estimation of Optimal Transport Maps from Paired Data in Gaussian Spaces — arXiv:2609.09089},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09089},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98403cd24237; sha256 590c093d7abfea0c3e58797033401f5914c20498c4676c26f3548990ffdb4c19},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09089. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the estimation of infinite-dimensional optimal transport maps from noisy paired observations. The population map pushes a Gaussian reference measure forward to a target probability measure on a function space and takes the Cameron--Martin gradient form $T=I+\nabla_{\mathcal H}\phi$. Our estimator uses cylindrical gradient sieves based on finitely many Cameron--Martin coordinates, thereby reducing the problem to finite-dimensional empirical risk minimization. A local nonasymptotic oracle inequality separates cylindrical approximation and statistical estimation errors while accounting for the conditioning of the parametrization. The approximation analysis relies on regularity conditions governing coordinate decay and dependence on omitted input coordinates. For diagonal Gaussian and nonlinear block-interaction classes, we derive matching upper and lower bounds that establish the minimax rate $N^{-s/(2s+1)}$ in expected norm, where $s$ measures weighted coordinate regularity. We further analyze a continuous two-groups model with Gaussian--Laplace mixtures and derive a prediction-risk bound for the resulting transport-map estimator.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in stat.ME).
Categorie arXiv: Statistics Theory (math.ST) ; Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2609.09089 — 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 2026-10-16T13:59:27.941Z dalla pagina https://arxiv.org/catchup/stat.ME/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).