paper-with-me

Papers

Localized Schrödinger Bridge Sampler

2024-09-12 · Georg A. Gottwald, Sebastian Reich

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 Schr\"odinger 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 Schr\"odinger bridge problem by $d$ low-dimensional Schr\"odinger bridge problems over the available training samples. In this context, a connection to multi-head self attention transformer architectures is established. As for the original Schr\"odinger bridge sampling approach, the localized sampler is stable and geometric 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.

📄 PDF Abstract BibTeX arXiv:2409.07968

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceDenoising

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Discrete Adjoint Schrödinger Bridge Sampler

2026-02-09 · Wei Guo, Yuchen Zhu, Xiaochen Du, Juno Nam 외 arxiv

Learning discrete neural samplers is challenging due to the lack of gradients and combinatorial complexity. While stochastic optimal control (SOC) and Schrödinger bridge (SB) provide principled solutions, efficient SOC s…

Schrödinger Bridge Samplers

2019-12-31 · Espen Bernton, Jeremy Heng, Arnaud Doucet, Pierre E. Jacob

Consider a reference Markov process with initial distribution $\pi_{0}$ and transition kernels $\{M_{t}\}_{t\in[1:T]}$, for some $T\in\mathbb{N}$. Assume that you are given distribution $\pi_{T}$, which is not equal to t…

Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers

2026-05-15 · Bruno Trentini, Dejan Stancevic, Michael M. Bronstein, Alexander Tong 외 arxiv

For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching and Schrödinger bridges define probabilit…

Schrödinger Bridge with Quadratic State Cost is Exactly Solvable

2024-06-01 · Alexis M. H. Teter, Wenqing Wang, Abhishek Halder

Schr\"{o}dinger bridge is a diffusion process that steers a given distribution to another in a prescribed time while minimizing the effort to do so. It can be seen as the stochastic dynamical version of the optimal mass …

Stable generative modeling using Schrödinger bridges

2024-01-09 · Georg A. Gottwald, Fengyi Li, Youssef Marzouk, Sebastian Reich

We consider the problem of sampling from an unknown distribution for which only a sufficiently large number of training samples are available. Such settings have recently drawn considerable interest in the context of gen…

Bayesian Inference