Metraipolis › archive › dc_7b797cdc4c4a
Information Spreading in Diffusion Models from Effective Field Theory — arXiv:2608.14308
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14308
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:48:50.232Z
- SHA-256 of the archived text
a65b9f8674b2d5a78e1e4bca79fa17bc10512ac22e79cd0c0fb443bd3b99a18d- Stable URL of this page
https://metraipolis.com/documento/dc_7b797cdc4c4a
How to cite
Information Spreading in Diffusion Models from Effective Field Theory — arXiv:2608.14308 — arXiv (en), https://arxiv.org/abs/2608.14308 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b797cdc4c4a (Metraipolis archive dc_7b797cdc4c4a, sha256 a65b9f8674b2d5a78e1e4bca79fa17bc10512ac22e79cd0c0fb443bd3b99a18d)
BibTeX
@misc{dc7b797cdc4c4a,
title = {Information Spreading in Diffusion Models from Effective Field Theory — arXiv:2608.14308},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14308},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b797cdc4c4a; sha256 a65b9f8674b2d5a78e1e4bca79fa17bc10512ac22e79cd0c0fb443bd3b99a18d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14308. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study score-matching diffusion models with a convolutional architecture. We argue that the inductive bias of locality means that the machinery of effective field theory from physics can be usefully applied to describe the denoising dynamics. We apply this formalism first to a simple toy example which permits an analytical description, and thereafter to MNIST, and show that in both cases, the mutual information between two points grows in a manner predicted by a simple effective field theory of Brownian motion. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG). Categorie arXiv: High Energy Physics - Theory (hep-th) ; Statistical Mechanics (cond-mat.stat-mech); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.14308 — 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 2026-10-18T14:47:59.429Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).