Metraipolis › archive › dc_e0d2fb4848dc

A Discrete-Time Variational Objective for Degenerate Diffusion and Equivalence to Flow Matching — arXiv:2611.00800

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00800
License (as archived)
CC0-1.0
Archived
2026-11-03T10:22:02.444Z
SHA-256 of the archived text
a9102d6fed53bc94e963aaa468d79d38a53520e5293453f06d05a5e5063bfd2a
Stable URL of this page
https://metraipolis.com/documento/dc_e0d2fb4848dc

How to cite

A Discrete-Time Variational Objective for Degenerate Diffusion and Equivalence to Flow Matching — arXiv:2611.00800 — arXiv (en), https://arxiv.org/abs/2611.00800 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e0d2fb4848dc (Metraipolis archive dc_e0d2fb4848dc, sha256 a9102d6fed53bc94e963aaa468d79d38a53520e5293453f06d05a5e5063bfd2a)
BibTeX
@misc{dce0d2fb4848dc,
  title = {A Discrete-Time Variational Objective for Degenerate Diffusion and Equivalence to Flow Matching — arXiv:2611.00800},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00800},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e0d2fb4848dc; sha256 a9102d6fed53bc94e963aaa468d79d38a53520e5293453f06d05a5e5063bfd2a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00800. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models and more recently Flow models have widespread application. In this work we consider degenerate Diffusion models in which the per-step generator is deterministic. We construct a modified variational framework and show a formal equivalence between Flow models and Degenerate Diffusion models. For our discrete-time variational objective we show that the optimal degenerate generator recovers the data distribution in the limit of an infinite number of generator steps. Our work therefore provides a unified perspective, showing that discrete-time implementations of flow matching and the discrete-time Degenerate Diffusion model can be considered within the same simple variational framework, removing the need for the continuous-time machinery normally used to justify flow matching models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00800 — 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 2026-11-03T10:19:49.792Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).