Metraipolis › archive › dc_7cc71d1ec125

Generative Diffusion Surrogates with Analytical Variance Schedule — arXiv:2609.01705

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01705
License (as archived)
CC0-1.0
Archived
2026-10-17T04:55:02.737Z
SHA-256 of the archived text
8a5d727aa9b1eb956dc6ed9a01e250049c91cfdf29432ccbb4da66651c5cf2f5
Stable URL of this page
https://metraipolis.com/documento/dc_7cc71d1ec125

How to cite

Generative Diffusion Surrogates with Analytical Variance Schedule — arXiv:2609.01705 — arXiv (en), https://arxiv.org/abs/2609.01705 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cc71d1ec125 (Metraipolis archive dc_7cc71d1ec125, sha256 8a5d727aa9b1eb956dc6ed9a01e250049c91cfdf29432ccbb4da66651c5cf2f5)
BibTeX
@misc{dc7cc71d1ec125,
  title = {Generative Diffusion Surrogates with Analytical Variance Schedule — arXiv:2609.01705},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01705},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cc71d1ec125; sha256 8a5d727aa9b1eb956dc6ed9a01e250049c91cfdf29432ccbb4da66651c5cf2f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01705. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Stochastic transport describes physical systems in which an initially structured distribution spreads under unresolved forcing, scattering, or heterogeneous media. Useful surrogates for such systems should be probabilistic, time-resolved, and able to represent non-Gaussian distributional structure. Generative diffusion models, which corrupt data with Gaussian noise and learn a reverse flow back to structured states, have these properties. Their noise schedules, however, are usually chosen heuristically: image and audio generation---the canonical use cases---provide no physical clock. In transport, by contrast, the variance, or mean-square displacement, is often known from macroscopic theory or empirical scaling even when the full distribution is not. Here we prescribe the forward noising rate as the time derivative of this variance, turning generative time into a calibrated transport clock. The variance path is enforced by construction, while the learned score field represents how non-Gaussian structure inherited from entrance data is smoothed along that path, requiring no intermediate-time physical transport data. For ballistic-to-diffusive transport in turbulent plasmas, the surrogate matches test-particle distributions, reproduces the laboratory-measured variance scale, and tracks the simulated kurtosis evolution without schedule tuning, enabling calibrated emulation and likelihood-based inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Instrumentation and Methods for Astrophysics (astro-ph.IM); Plasma Physics (physics.plasm-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.01705 — 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 2026-10-17T04:09:43.287Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).