Saved in:
Bibliographic Details
Main Authors: Yang, Gefan, van der Meulen, Frank, Sommer, Stefan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.11909
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912440862638080
author Yang, Gefan
van der Meulen, Frank
Sommer, Stefan
author_facet Yang, Gefan
van der Meulen, Frank
Sommer, Stefan
contents We propose a novel method for simulating conditioned diffusion processes (diffusion bridges) in Euclidean spaces. By training a neural network to approximate bridge dynamics, our approach eliminates the need for computationally intensive Markov Chain Monte Carlo (MCMC) methods or score modeling. Compared to existing methods, it offers greater robustness across various diffusion specifications and conditioning scenarios. This applies in particular to rare events and multimodal distributions, which pose challenges for score-learning- and MCMC-based approaches. We introduce a flexible variational family, partially specified by a neural network, for approximating the diffusion bridge path measure. Once trained, it enables efficient sampling of independent bridges at a cost comparable to sampling the unconditioned (forward) process.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11909
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Guided Diffusion Bridges
Yang, Gefan
van der Meulen, Frank
Sommer, Stefan
Machine Learning
We propose a novel method for simulating conditioned diffusion processes (diffusion bridges) in Euclidean spaces. By training a neural network to approximate bridge dynamics, our approach eliminates the need for computationally intensive Markov Chain Monte Carlo (MCMC) methods or score modeling. Compared to existing methods, it offers greater robustness across various diffusion specifications and conditioning scenarios. This applies in particular to rare events and multimodal distributions, which pose challenges for score-learning- and MCMC-based approaches. We introduce a flexible variational family, partially specified by a neural network, for approximating the diffusion bridge path measure. Once trained, it enables efficient sampling of independent bridges at a cost comparable to sampling the unconditioned (forward) process.
title Neural Guided Diffusion Bridges
topic Machine Learning
url https://arxiv.org/abs/2502.11909