Metraipolis › archive › dc_5c481ac7965e
Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective — arXiv:2609.06947
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06947
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:57:36.609Z
- SHA-256 of the archived text
8e0c2a99f61f71340a4f4d34bdf28ebac4af4cea875cd8fcd5372a59906afff1- Stable URL of this page
https://metraipolis.com/documento/dc_5c481ac7965e
How to cite
Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective — arXiv:2609.06947 — arXiv (en), https://arxiv.org/abs/2609.06947 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5c481ac7965e (Metraipolis archive dc_5c481ac7965e, sha256 8e0c2a99f61f71340a4f4d34bdf28ebac4af4cea875cd8fcd5372a59906afff1)
BibTeX
@misc{dc5c481ac7965e,
title = {Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective — arXiv:2609.06947},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06947},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5c481ac7965e; sha256 8e0c2a99f61f71340a4f4d34bdf28ebac4af4cea875cd8fcd5372a59906afff1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06947. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Flow matching, together with classifier-free guidance (CFG), is widely used in generative modeling, yet much of the theoretical understanding remains distribution-wise. Since practical sampling follows individual trajectories, distribution-level guarantees alone do not fully capture how trajectories interact with the data geometry or how guidance reshapes it. To overcome this limitation, we establish a unified stagewise geometric theory of attraction and absorption for both continuous dynamics and explicit Euler discretization. Specifically, with $t\in[0,1]$ running from noise to data, we show that unconditional flow trajectories are successively attracted toward a neighborhood of the global mean, the data convex hull, and a neighborhood of a possibly nonconvex local cluster. Across these stages, the corresponding distance satisfies a common contraction estimate, yielding an ${O}(1-t)$ decay of the distance in the final stage. For CFG, the same structure persists with an extrapolated mean, an inflated conditional convex hull, and, near the target cluster, the restored local geometry of conditional flow matching. We further show that a general time schedule $a(t)$ replaces the $O(1-t)$ decay by $O(1-a(t))$. Together, these results provide a unified particle-level geometric account of flow matching and CFG across continuous and discrete sampling.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.06947 — 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 2026-10-16T13:39:42.921Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).