Metraipolis › archive › dc_fd752960eaf3
Generative diffusion in long-range correlated landscapes: Speciation cascade and the foam structure of the score — arXiv:2611.02955
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02955
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:41:24.133Z
- SHA-256 of the archived text
e7df1ba1f484baa8ff7fc6f3ff3b672eb8ee30b8d45024f96d7cf66b17baf847- Stable URL of this page
https://metraipolis.com/documento/dc_fd752960eaf3
How to cite
Generative diffusion in long-range correlated landscapes: Speciation cascade and the foam structure of the score — arXiv:2611.02955 — arXiv (en), https://arxiv.org/abs/2611.02955 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd752960eaf3 (Metraipolis archive dc_fd752960eaf3, sha256 e7df1ba1f484baa8ff7fc6f3ff3b672eb8ee30b8d45024f96d7cf66b17baf847)
BibTeX
@misc{dcfd752960eaf3,
title = {Generative diffusion in long-range correlated landscapes: Speciation cascade and the foam structure of the score — arXiv:2611.02955},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02955},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd752960eaf3; sha256 e7df1ba1f484baa8ff7fc6f3ff3b672eb8ee30b8d45024f96d7cf66b17baf847},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02955. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While state of the art for image and video generation, the fundamental reasons for the effectiveness of generative diffusion remain unclear. In particular, the observed advantage of following an entire reverse process with respect to single-shot or autoregressive methods, and for what type of data it may hold, is not well understood. In this work, we aim to better understand the role of the reverse process by considering a complex yet analytically tractable data model, the Gibbs measure of a high-dimensional Gaussian random potential with long-range correlations. Focusing on the exact score, we show that the speciation threshold, in which a trajectory commits to one class of the data, becomes a speciation window, in which the reverse process progressively resolves the Parisi tree of pure states of the full replica-symmetry breaking measure, committing to ever finer branches down to a single pure state. Importantly, these commitments take place at noise levels where the noisy sample distinguishes the pure states only through an energy of order one, beyond the reach of standard replica saddle points. Constructing a Larkin argument suited to such $O(1)$ energy gaps, we describe the score as a foam, with slab-like cells separated by shock-like boundaries. In the variance-exploding process we consider, this window is followed by a shrinkage of the samples towards the data support, and finally by reconstruction within the selected pure state. The denoising error of the exact score follows these stages, dropping during the speciation window with a profile set by the Parisi function alone, and then within the selected state. We believe that the generative foam we describe, and in particular the boundaries between cells, could play an important role in determining where the errors of trained diffusion models redistribute the mass of the generated samples when the data are long-range correlated. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Statistical Mechanics (cond-mat.stat-mech); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.02955 — 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 2026-11-03T18:12:54.791Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).