Metraipolis › archive › dc_7a0debca01a6
Discrete Wasserstein Flows for One-Step Generative Modeling — arXiv:2610.01355
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01355
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:13:38.625Z
- SHA-256 of the archived text
8c720d527ccc44132b86dd90202869a3c832923ddbeaa56c50193435d8367127- Stable URL of this page
https://metraipolis.com/documento/dc_7a0debca01a6
How to cite
Discrete Wasserstein Flows for One-Step Generative Modeling — arXiv:2610.01355 — arXiv (en), https://arxiv.org/abs/2610.01355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a0debca01a6 (Metraipolis archive dc_7a0debca01a6, sha256 8c720d527ccc44132b86dd90202869a3c832923ddbeaa56c50193435d8367127)
BibTeX
@misc{dc7a0debca01a6,
title = {Discrete Wasserstein Flows for One-Step Generative Modeling — arXiv:2610.01355},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01355},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a0debca01a6; sha256 8c720d527ccc44132b86dd90202869a3c832923ddbeaa56c50193435d8367127},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define a target-relative KL gradient flow over the transitions of a reversible Markov kernel. We realize this probability flow at the particle level through Markov jumps and amortize the resulting transport updates into a latent-conditioned generator, so that the iterative dynamics are required only during training while inference remains one-step. In a controlled setting where the underlying distributions and transport dynamics can be computed exactly, we verify KL dissipation, consistency between the particle dynamics and the probability flow, and the predicted numerical scaling. We further show that a finite-capacity neural generator can track these exact transport targets while retaining one-step generation. These results validate the basic construction and provide a foundation for scaling Discrete Drifting to structured discrete data. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.01355 — 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 2026-10-06T10:21:28.179Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).