Metraipolis › archive › dc_b4ae41be67ac

Same Flow, Different Paths: Variance Reduction in Flow Matching — arXiv:2609.17287

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17287
License (as archived)
CC0-1.0
Archived
2026-10-15T20:46:01.109Z
SHA-256 of the archived text
5392b2ee4b0dbf77261617a03a9e9d98a17164e3d33ce66f42625d2e52e76ef1
Stable URL of this page
https://metraipolis.com/documento/dc_b4ae41be67ac

How to cite

Same Flow, Different Paths: Variance Reduction in Flow Matching — arXiv:2609.17287 — arXiv (en), https://arxiv.org/abs/2609.17287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b4ae41be67ac (Metraipolis archive dc_b4ae41be67ac, sha256 5392b2ee4b0dbf77261617a03a9e9d98a17164e3d33ce66f42625d2e52e76ef1)
BibTeX
@misc{dcb4ae41be67ac,
  title = {Same Flow, Different Paths: Variance Reduction in Flow Matching — arXiv:2609.17287},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17287},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b4ae41be67ac; sha256 5392b2ee4b0dbf77261617a03a9e9d98a17164e3d33ce66f42625d2e52e76ef1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In flow matching (FM), a velocity model $v_{\theta}$ is trained using a predefined path $g_t$ that connects data and noise samples (e.g., $g_t(x_0, x_1) = (1 - t) x_0 + t x_1$). In this work, we study the choice of this path from an optimization perspective by analyzing the variance of stochastic gradients. We consider the class $G(p_t,v^\star_t)$ of paths that induce the same marginal distributions $p_t$ and marginal velocity field $v^\star_t$, and therefore the same FM objective. Our main finding is that the choice of path $g_t$ can fundamentally change the convergence rate of SGD, even when the FM objective remains exactly the same. (i) For a linear velocity model and one-dimensional Gaussian data, we derive a tight bound on the SGD iteration complexity up to logarithmic factors and find an analytically optimal path that minimizes this bound among linear paths inducing the same FM problem. (ii) We then extend the variance analysis to general FM problems and formulate path selection at a fixed $\theta$ as the variance-minimization problem PathOpt$_\theta$, constrained to $g_t\in G(p_t,v^\star_t)$. We show that this constraint is essential: reducing variance without it can lead to slower convergence. (iii) Since the constraint $g_t \in G(p_t,v^\star_t)$ cannot generally be verified directly, we derive an equivalent formulation with constraints that can be estimated from samples, allowing paths to be found numerically. Our theoretical results are supported by experiments with Gaussian data, Gaussian mixture models, and real datasets.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-16 in math.OC).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.17287 — 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 2026-10-15T19:36:35.870Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).