Abstract:Pretrained diffusion models provide powerful learned priors, but in scientific sampling the target distribution often depends on physical context that is not fully represented by one generative model. We introduce Generative Gibbs for Physics-Aware Sampling (GG-PA), a training-free framework that formulates the composition of learned partial priors and explicit physical context as inference over a joint target distribution in an augmented state space. We derive a Gibbs sampler for this joint target, show that it is asymptotically exact as the diffusion time approaches zero, and prove that in settings with quadratic interactions it remains exact at finite diffusion times. We further introduce replica exchange over diffusion time to accelerate mixing. Experiments on a double-well system, a $\phi^4$ lattice model, and atomistic peptide systems show that GG-PA recovers context-induced distribution shifts and emergent collective behavior in interacting systems using partial priors without retraining. These results demonstrate GG-PA as a practical approach for combining pretrained generative priors with explicit physical context.
| Comments: | 31 pages, 11 figures |
| Subjects: | Machine Learning (cs.LG); Statistical Mechanics (cond-mat.stat-mech) |
| Cite as: | arXiv:2605.10642 [cs.LG] |
| (or arXiv:2605.10642v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10642 arXiv-issued DOI via DataCite (pending registration) |
From: Aaron Dinner [view email]
[v1]
Mon, 11 May 2026 14:29:20 UTC (14,583 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。