Metraipolis › archive › dc_02a4cf9eb01a

Discrete Action Matching: Learning Stochastic Dynamics from Samples via State Graphs — arXiv:2610.05071

Source
arXiv
Original
https://arxiv.org/abs/2610.05071
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:39.044Z
SHA-256 of the archived text
d54ec958af3320b46e8daf7df75abe3c88598890be527f10987210db43d8d2a8
Stable URL of this page
https://metraipolis.com/documento/dc_02a4cf9eb01a

How to cite

Discrete Action Matching: Learning Stochastic Dynamics from Samples via State Graphs — arXiv:2610.05071 — arXiv, https://arxiv.org/abs/2610.05071 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02a4cf9eb01a (Metraipolis archive dc_02a4cf9eb01a, sha256 d54ec958af3320b46e8daf7df75abe3c88598890be527f10987210db43d8d2a8)
BibTeX
@misc{dc02a4cf9eb01a,
  title = {Discrete Action Matching: Learning Stochastic Dynamics from Samples via State Graphs — arXiv:2610.05071},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05071},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02a4cf9eb01a; sha256 d54ec958af3320b46e8daf7df75abe3c88598890be527f10987210db43d8d2a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05071. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning population dynamics from unpaired temporal marginals is an ill-posed inverse problem that requires structural assumptions on the underlying dynamics. We introduce $\textit{Discrete Action Matching}$ (DAM), a finite-state counterpart of Action Matching based on discrete Wasserstein geometry. For a prescribed marginal path and transport geometry, we derive an action-minimization objective for its canonical minimum-kinetic-energy current. Our key observation is that the density dependence of the discrete action reduces to neighboring density ratios. Along an empirical interpolation of the snapshots, DAM first estimates these ratios and then learns an action potential. The learned fields also define a graph-supported Markov sampler. Experiments on controlled synthetic dynamics and real mouse gastrulation data evaluate marginal reconstruction and interpolation. Additional experiments approximate numerical surface-transport paths from paired samples.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05071 — 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 2026-10-06T05:24:05.962Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).