Metraipolis › archive › dc_a2df8538bb96

Beyond Transport Cost: Routing Differences between Flow Matching and Optimal Transport — arXiv:2610.05921

Source
arXiv
Original
https://arxiv.org/abs/2610.05921
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:20.836Z
SHA-256 of the archived text
cf9a00397ed847d63b7e20d1a0dfc9154fe23a079311478820a67473bdc7421e
Stable URL of this page
https://metraipolis.com/documento/dc_a2df8538bb96

How to cite

Beyond Transport Cost: Routing Differences between Flow Matching and Optimal Transport — arXiv:2610.05921 — arXiv, https://arxiv.org/abs/2610.05921 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2df8538bb96 (Metraipolis archive dc_a2df8538bb96, sha256 cf9a00397ed847d63b7e20d1a0dfc9154fe23a079311478820a67473bdc7421e)
BibTeX
@misc{dca2df8538bb96,
  title = {Beyond Transport Cost: Routing Differences between Flow Matching and Optimal Transport — arXiv:2610.05921},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05921},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2df8538bb96; sha256 cf9a00397ed847d63b7e20d1a0dfc9154fe23a079311478820a67473bdc7421e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05921. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In generative models, Optimal Transport (OT) is used to improve Flow Matching (FM) by reducing noise-data coupling cost. However, different noise-to-output assignments can yield nearly equal costs, raising a key question. Is cost alone sufficient to guide coupling design? We address this question by separating transport cost from routing, i.e., the destination reached by each noise sample. We show numerically how FM and OT can differ in routing while remaining close in cost. We examine its consequences in learned neural FM. Using the exact FM routing as an oracle, we further construct a routing-aware training coupling and find that it yields a directionally consistent improvement in generation over a cost-matched, cost-only counterpart. Our findings highlight what cost minimization can overlook and motivate using both cost and routing to evaluate the design of OT-based FM couplings. Code will be released upon acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.05921 — 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 2026-10-06T05:27:05.838Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).