Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mialon, Grégoire, Garrido, Quentin, Lawrence, Hannah, Rehman, Danyal, LeCun, Yann, Kiani, Bobak T.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917589505015808
author Mialon, Grégoire
Garrido, Quentin
Lawrence, Hannah
Rehman, Danyal
LeCun, Yann
Kiani, Bobak T.
author_facet Mialon, Grégoire
Garrido, Quentin
Lawrence, Hannah
Rehman, Danyal
LeCun, Yann
Kiani, Bobak T.
contents Machine learning for differential equations paves the way for computationally efficient alternatives to numerical solvers, with potentially broad impacts in science and engineering. Though current algorithms typically require simulated training data tailored to a given setting, one may instead wish to learn useful information from heterogeneous sources, or from real dynamical systems observations that are messy or incomplete. In this work, we learn general-purpose representations of PDEs from heterogeneous data by implementing joint embedding methods for self-supervised learning (SSL), a framework for unsupervised representation learning that has had notable success in computer vision. Our representation outperforms baseline approaches to invariant tasks, such as regressing the coefficients of a PDE, while also improving the time-stepping performance of neural solvers. We hope that our proposed methodology will prove useful in the eventual development of general-purpose foundation models for PDEs. Code: https://github.com/facebookresearch/SSLForPDEs.
format Preprint
id arxiv_https___arxiv_org_abs_2307_05432
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
Mialon, Grégoire
Garrido, Quentin
Lawrence, Hannah
Rehman, Danyal
LeCun, Yann
Kiani, Bobak T.
Machine Learning
Numerical Analysis
Machine learning for differential equations paves the way for computationally efficient alternatives to numerical solvers, with potentially broad impacts in science and engineering. Though current algorithms typically require simulated training data tailored to a given setting, one may instead wish to learn useful information from heterogeneous sources, or from real dynamical systems observations that are messy or incomplete. In this work, we learn general-purpose representations of PDEs from heterogeneous data by implementing joint embedding methods for self-supervised learning (SSL), a framework for unsupervised representation learning that has had notable success in computer vision. Our representation outperforms baseline approaches to invariant tasks, such as regressing the coefficients of a PDE, while also improving the time-stepping performance of neural solvers. We hope that our proposed methodology will prove useful in the eventual development of general-purpose foundation models for PDEs. Code: https://github.com/facebookresearch/SSLForPDEs.
title Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2307.05432