Metraipolis › archive › dc_6d75a2cdb49d
CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching — arXiv:2609.14171
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14171
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:10:37.348Z
- SHA-256 of the archived text
0e949f3fe3650e96d19e8e64b100d964fe4d6f48e2cf6a0c82bd973f39f5e2c4- Stable URL of this page
https://metraipolis.com/documento/dc_6d75a2cdb49d
How to cite
CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching — arXiv:2609.14171 — arXiv (en), https://arxiv.org/abs/2609.14171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6d75a2cdb49d (Metraipolis archive dc_6d75a2cdb49d, sha256 0e949f3fe3650e96d19e8e64b100d964fe4d6f48e2cf6a0c82bd973f39f5e2c4)
BibTeX
@misc{dc6d75a2cdb49d,
title = {CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching — arXiv:2609.14171},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14171},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6d75a2cdb49d; sha256 0e949f3fe3650e96d19e8e64b100d964fe4d6f48e2cf6a0c82bd973f39f5e2c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Complex-valued signals like MRI and audio spectrograms are typically modelled as flat two-channel Euclidean data. The inherited Euclidean metric $dA^2 + A^2 d\theta^2$ vanishes at the origin, leaving phase unpenalised exactly where the signal is weakest. We replace it with the decoupled product metric $dA^2 + d\theta^2$ on the cylindrical closure $[0, \infty) \times S^1$, which stays non-degenerate at $A = 0$. We measure what this substitution costs and buys. Exact analytical bridges across synthetic fields, fastMRI knee data, and LibriSpeech spectrograms show Cartesian paths induce a heavy-tailed angular velocity distribution (Pareto index $\approx 1$). Under independent coupling, 43%-49% of signal energy falls on paths turning faster than $\pi$ rad per unit time. Cylindrical paths never reach this speed. We formulate Cylindrical Flow Matching (CyFM) to strictly bound the angular regression target, coupling noise and data via exact minibatch Optimal Transport jointly over whole fields. This coupling reduces few-step generation error by 3%-60%. CyFM achieves lower generative error than the best Cartesian baseline at every step up to $k = 8$ on synthetic fields and speech spectrograms, with all seeds separated. On knee MRI, the single-step advantage is 1.8x. At convergence ($k = 100$), the two geometries show no significant difference. Finally, a prior-only control exposes the cost of flat parametrisation: on synthetic fields, a single Cartesian Euler step performs worse than the unintegrated noise prior (0.376 vs. 0.150). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.14171 — 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 2026-10-15T23:54:14.675Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).