Metraipolis › archive › dc_3a157c304bee
Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching — arXiv:2609.39488
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39488
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:46:16.524Z
- SHA-256 of the archived text
c92f5420ebd8dc0df78ef67795c97ac0a2a8d1e896641ad36a69bba13fd484b7- Stable URL of this page
https://metraipolis.com/documento/dc_3a157c304bee
How to cite
Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching — arXiv:2609.39488 — arXiv (en), https://arxiv.org/abs/2609.39488 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a157c304bee (Metraipolis archive dc_3a157c304bee, sha256 c92f5420ebd8dc0df78ef67795c97ac0a2a8d1e896641ad36a69bba13fd484b7)
BibTeX
@misc{dc3a157c304bee,
title = {Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching — arXiv:2609.39488},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39488},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a157c304bee; sha256 c92f5420ebd8dc0df78ef67795c97ac0a2a8d1e896641ad36a69bba13fd484b7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39488. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Flow matching generates samples by gradually transforming noise into data. In practice, using a finite number of sampling steps introduces a numerical error that depends on the chosen schedule. We study this dependence for Gaussian targets and the explicit midpoint sampling method, using the exact flow field. We measure sampling error by the squared Wasserstein distance between the target distribution and the final distribution produced by the midpoint sampler. We show that the standard conditional optimal transport (CondOT) schedule cancels the leading midpoint error and improves the general convergence bound, even when the sampling steps are unequally spaced. On a uniform grid of $S$ sampling steps, we fix the signal schedule at $\alpha_t=t$ and prove the existence of scalar noise schedules $\beta_t$ that approach the CondOT noise schedule $1-t$ at rate $1/S$ and yield exact Gaussian sampling for every sufficiently large $S$. Controlled Gaussian experiments illustrate the convergence rates and exact calibration. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39488 — 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 2026-10-07T13:18:10.396Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).