Particle-Guided Diffusion Models for Partial Differential Equations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Millard, Andrew, Lindsten, Fredrik, Zhao, Zheng
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911723948081152
author Millard, Andrew
Lindsten, Fredrik
Zhao, Zheng
author_facet Millard, Andrew
Lindsten, Fredrik
Zhao, Zheng
contents We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial differential equation (PDE) residuals and observational constraints, ensuring generated samples remain physically admissible. We embed this sampling procedure within a new Sequential Monte Carlo (SMC) framework, yielding a scalable generative PDE solver. Across multiple benchmark PDE systems as well as multiphysics and interacting PDE systems, our method produces solution fields with lower numerical error than existing state-of-the-art generative methods.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23262
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Particle-Guided Diffusion Models for Partial Differential Equations
Millard, Andrew
Lindsten, Fredrik
Zhao, Zheng
Machine Learning
We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial differential equation (PDE) residuals and observational constraints, ensuring generated samples remain physically admissible. We embed this sampling procedure within a new Sequential Monte Carlo (SMC) framework, yielding a scalable generative PDE solver. Across multiple benchmark PDE systems as well as multiphysics and interacting PDE systems, our method produces solution fields with lower numerical error than existing state-of-the-art generative methods.
title Particle-Guided Diffusion Models for Partial Differential Equations
topic Machine Learning
url https://arxiv.org/abs/2601.23262