.png){kind=icon}
.png){kind=icon}
Return
Localized Schrödinger Bridge Sampler
.png){kind=icon}
OA
AI
DOI：10.1016/j.jcp.2025.114583.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We consider the problem of sampling from an unknown distribution for which only a sufficiently large number of training samples are available. In this paper, we build on previous work combining Schrödinger bridges and plug & play Langevin samplers. A key bottleneck of these approaches is the exponential dependence of the required training samples on the dimension, d, of the ambient state space. We propose a localization strategy which exploits conditional independence of conditional expectation values. Localization thus replaces a single high-dimensional Schrödinger bridge problem by d low-dimensional Schrödinger bridge problems over the available training samples. As for the original Schrödinger bridge sampling approach, the localized sampler is stable and geometrically ergodic. The sampler also naturally extends to conditional sampling and to Bayesian inference. We demonstrate the performance of our proposed scheme through experiments on a high-dimensional Gaussian problem, on a temporal stochastic process, and on a stochastic subgrid-scale parametrization conditional sampling problem. We also extend the idea of localization to plug & play Langevin samplers using kernel-based denoising in combination with Tweedie’s formula.
Keywords:
generative modeling
Langevin dynamics
denoising
Schrödinger bridges
conditional independence
localization
Bayesian inference
conditional sampling
multi-scale closure
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.8
Papers:
1.5W
Citations:
7.4W