DiffusionPDE: Generative PDE-Solving Under Partial Observation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Jiahe, Yang, Guandao, Wang, Zichen, Park, Jeong Joon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910679786586112
author Huang, Jiahe
Yang, Guandao
Wang, Zichen
Park, Jeong Joon
author_facet Huang, Jiahe
Yang, Guandao
Wang, Zichen
Park, Jeong Joon
contents We introduce a general framework for solving partial differential equations (PDEs) using generative diffusion models. In particular, we focus on the scenarios where we do not have the full knowledge of the scene necessary to apply classical solvers. Most existing forward or inverse PDE approaches perform poorly when the observations on the data or the underlying coefficients are incomplete, which is a common assumption for real-world measurements. In this work, we propose DiffusionPDE that can simultaneously fill in the missing information and solve a PDE by modeling the joint distribution of the solution and coefficient spaces. We show that the learned generative priors lead to a versatile framework for accurately solving a wide range of PDEs under partial observation, significantly outperforming the state-of-the-art methods for both forward and inverse directions.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17763
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffusionPDE: Generative PDE-Solving Under Partial Observation
Huang, Jiahe
Yang, Guandao
Wang, Zichen
Park, Jeong Joon
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Numerical Analysis
We introduce a general framework for solving partial differential equations (PDEs) using generative diffusion models. In particular, we focus on the scenarios where we do not have the full knowledge of the scene necessary to apply classical solvers. Most existing forward or inverse PDE approaches perform poorly when the observations on the data or the underlying coefficients are incomplete, which is a common assumption for real-world measurements. In this work, we propose DiffusionPDE that can simultaneously fill in the missing information and solve a PDE by modeling the joint distribution of the solution and coefficient spaces. We show that the learned generative priors lead to a versatile framework for accurately solving a wide range of PDEs under partial observation, significantly outperforming the state-of-the-art methods for both forward and inverse directions.
title DiffusionPDE: Generative PDE-Solving Under Partial Observation
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Numerical Analysis
url https://arxiv.org/abs/2406.17763