Metraipolis › archive › dc_09ec93e501e6
Probability flow ODEs in score-based and reflected diffusion models — arXiv:2610.03846
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03846
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:31:55.647Z
- SHA-256 of the archived text
830a9ce11bcd8c0240635416dc4990c37b3548f8464dbeacd814e111b0b830c4- Stable URL of this page
https://metraipolis.com/documento/dc_09ec93e501e6
How to cite
Probability flow ODEs in score-based and reflected diffusion models — arXiv:2610.03846 — arXiv, https://arxiv.org/abs/2610.03846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09ec93e501e6 (Metraipolis archive dc_09ec93e501e6, sha256 830a9ce11bcd8c0240635416dc4990c37b3548f8464dbeacd814e111b0b830c4)
BibTeX
@misc{dc09ec93e501e6,
title = {Probability flow ODEs in score-based and reflected diffusion models — arXiv:2610.03846},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03846},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09ec93e501e6; sha256 830a9ce11bcd8c0240635416dc4990c37b3548f8464dbeacd814e111b0b830c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Probability-flow ordinary differential equations (PF-ODEs) are widely used as deterministic samplers for score-based diffusion models. Their usual justification is that the Fokker--Planck equation of a diffusion can be rewritten as a continuity equation driven by the score function of the forward diffusion. This identity does not, however, guarantee that the resulting velocity field generates a well-posed flow. We provide theoretical insights into the design of such deterministic samplers for generative models based on diffusions and reflected diffusions. We identify sufficient conditions for a regular Lagrangian PF-ODE flow to exist; reverse sampling and invertibility require two-sided divergence control. For learned scores, sampler stability is controlled by an unweighted velocity error, exposing a mismatch with density-weighted score matching and motivating architectural control of Jacobians, divergence, growth, and compression. Under the manifold hypothesis, positive-time regularization justifies an early-stopped PF-ODE while constants deteriorate near the data endpoint; an explicit sphere example shows that the exact deterministic flow becomes singular as the noise level vanishes even though the diffusion marginals remain well defined. These theoretical insights translate into concrete design principles for stable, invertible, and constraint-preserving diffusion samplers. We illustrate the practical relevance of these design principles using controlled numerical experiments. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Probability (math.PR). Pagina del lavoro: https://arxiv.org/abs/2610.03846 — 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 2026-10-06T05:27:05.931Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).