Metraipolis › archive › dc_04e07b3f993f

Conditional Flow Matching for Transport Between Markov Processes — arXiv:2610.07229

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07229
License (as archived)
CC0-1.0
Archived
2026-10-07T11:40:57.082Z
SHA-256 of the archived text
62687f1585f9f6497c5f29b6ec7222a6c4d722906e4e759b61c8fa347652e9c4
Stable URL of this page
https://metraipolis.com/documento/dc_04e07b3f993f

How to cite

Conditional Flow Matching for Transport Between Markov Processes — arXiv:2610.07229 — arXiv (en), https://arxiv.org/abs/2610.07229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_04e07b3f993f (Metraipolis archive dc_04e07b3f993f, sha256 62687f1585f9f6497c5f29b6ec7222a6c4d722906e4e759b61c8fa347652e9c4)
BibTeX
@misc{dc04e07b3f993f,
  title = {Conditional Flow Matching for Transport Between Markov Processes — arXiv:2610.07229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_04e07b3f993f; sha256 62687f1585f9f6497c5f29b6ec7222a6c4d722906e4e759b61c8fa347652e9c4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Motivated by sequence-to-sequence transport in the context time-series domain adaptation, we study the problem of transportation between trajectories of Markov processes. Given a limited number of trajectories from source distribution and the target distribution, we formulate a flow matching based algorithm which learns a transport map from the source to target trajectory distribution, while preserving the Markov structure. We show that this is consistent in the population limit and derive finite-sample error bounds under mixing time assumptions, following the analysis of classical statistical problems including regression (Nagaraj et al., 2020), principal component analysis (Kumar and Sarkar, 2023), and matrix concentration (Neeman et al., 2024) in the Markov setting. We complement that with a lower-bound construction showing that a mixing-time dependent sample complexity is unavoidable even with regular Gaussian conditional transitions. We evaluate on synthetic and real-world data. For image retrieval from electroencephalography (EEG) on THINGS-EEG2 (Gifford et al., 2022), the task is to identify the viewed image from EEG signals captured from human subjects, which suffers from high inter subject variability. We augment the ENIGMA decoder (Kneeland et al., 2026) with a conditional flow before its subject-specific temporal map. This improves mean top-5 retrieval accuracy from 43.87% to 49.05%, an 11.82% relative improvement.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.07229 — 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 2026-10-07T11:19:24.738Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).