Particle-Guided Diffusion Models for Partial Differential Equations
By: Andrew Millard, Fredrik Lindsten, Zheng Zhao
Potential Business Impact:
Makes computer models follow science rules better.
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.
Similar Papers
Data-driven generative simulation of SDEs using diffusion models
Machine Learning (CS)
Creates realistic data for smarter money decisions.
Unifying and extending Diffusion Models through PDEs for solving Inverse Problems
Machine Learning (CS)
New math helps computers create realistic images.
Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation
Machine Learning (CS)
Makes AI better at solving science problems.