Metraipolis › archive › dc_560eaebef93c

Jumping up and down: Denoiser diffusion models for discrete ordinal data — arXiv:2610.02754

Source: arXiv
Original: https://arxiv.org/abs/2610.02754
License (as archived): CC0-1.0
Archived: 2026-10-05T23:09:49.035Z
SHA-256 of the archived text: 9221e7f99f300168536dfb4b243c9a88c18778fe777bfded378d53320abdf8f6
Stable URL of this page: https://metraipolis.com/documento/dc_560eaebef93c

How to cite

Jumping up and down: Denoiser diffusion models for discrete ordinal data — arXiv:2610.02754 — arXiv, https://arxiv.org/abs/2610.02754 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_560eaebef93c (Metraipolis archive dc_560eaebef93c, sha256 9221e7f99f300168536dfb4b243c9a88c18778fe777bfded378d53320abdf8f6)

BibTeX

@misc{dc560eaebef93c,
  title = {Jumping up and down: Denoiser diffusion models for discrete ordinal data — arXiv:2610.02754},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02754},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_560eaebef93c; sha256 9221e7f99f300168536dfb4b243c9a88c18778fe777bfded378d53320abdf8f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02754. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models are highly developed in continuous spaces for image and video domains. Recently, major advances have been made for discrete diffusion models for categorical data, specifically in the language domain. In contrast, diffusion models for discrete integer-valued data are less developed, despite the prevalence of this modality, ranging from images and music to gene counts. We introduce Jumping Up and Down (JUD)---a new family of denoiser-based diffusion models for discrete ordinal data. This is the first family of diffusion models for ordinal data which centers around training denoisers, which at the same time allows for bi-directional (up and down) perturbations of the data. The simplicity of the training objective, combined with the flexibility of bi-directional perturbations, leads us to obtain competitive results across different data modalities.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2610.02754 — 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 2026-10-05T23:01:38.627Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).