Metraipolis › archive › dc_2f5597df5bd7
PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation — arXiv:2609.40287
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.40287
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:47:01.122Z
- SHA-256 of the archived text
8cb28302557bc814abb3663a0a2dbd5116e4c70f4fdc8da0907d29a529683f34- Stable URL of this page
https://metraipolis.com/documento/dc_2f5597df5bd7
How to cite
PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation — arXiv:2609.40287 — arXiv (en), https://arxiv.org/abs/2609.40287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f5597df5bd7 (Metraipolis archive dc_2f5597df5bd7, sha256 8cb28302557bc814abb3663a0a2dbd5116e4c70f4fdc8da0907d29a529683f34)
BibTeX
@misc{dc2f5597df5bd7,
title = {PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation — arXiv:2609.40287},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.40287},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f5597df5bd7; sha256 8cb28302557bc814abb3663a0a2dbd5116e4c70f4fdc8da0907d29a529683f34},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Physics-constrained generative models aim to generate physical fields that match a target distribution and satisfy prescribed constraints. However, enforcing these constraints often increases sampling costs through iterative corrections or training costs through residual optimization and trajectory unrolling. To address this issue, we introduce \textbf{P}reconditioned \textbf{M}anifold \textbf{o}ne-\textbf{s}tep \textbf{F}low \textbf{M}atching (\textbf{PMosFM}), a preconditioned manifold matching framework for one-step physics-constrained generation. By encoding constraints in a manifold decoder, PMosFM learns transport in intrinsic coordinates without separate residual losses or terminal residual unrolling. A geometric preconditioner rescales coordinates using the decoder-induced metric, while a regularized covariance transform approximately whitens the interpolation-state inputs. A finite-interval objective couples velocity supervision with consistency between decoded endpoints in physical space. We show that exact parameterization removes residual-induced Gauss--Newton curvature, that geometric and covariance effects separate in a local conditioning bound, and that physical flow-map error bounds endpoint distributional error. Controlled ablations examine conditioning, and experiments evaluate optimizer-update time and memory footprint. At inference, PMosFM uses one neural transport evaluation followed by physical decoding. Experiments across benchmarks show lower training and sampling time than the multi-step baselines at comparable physical and distributional fidelity. Code and datasets will be released publicly.
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/2609.40287 — 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 2026-10-07T13:18:10.526Z 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).