Training Stiff Neural Ordinary Differential Equations with Implicit Single-Step Methods

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fronk, Colby, Petzold, Linda
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916426043883520
author Fronk, Colby
Petzold, Linda
author_facet Fronk, Colby
Petzold, Linda
contents Stiff systems of ordinary differential equations (ODEs) are pervasive in many science and engineering fields, yet standard neural ODE approaches struggle to learn them. This limitation is the main barrier to the widespread adoption of neural ODEs. In this paper, we propose an approach based on single-step implicit schemes to enable neural ODEs to handle stiffness and demonstrate that our implicit neural ODE method can learn stiff dynamics. This work addresses a key limitation in current neural ODE methods, paving the way for their use in a wider range of scientific problems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05592
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Training Stiff Neural Ordinary Differential Equations with Implicit Single-Step Methods
Fronk, Colby
Petzold, Linda
Numerical Analysis
Artificial Intelligence
Computational Engineering, Finance, and Science
Stiff systems of ordinary differential equations (ODEs) are pervasive in many science and engineering fields, yet standard neural ODE approaches struggle to learn them. This limitation is the main barrier to the widespread adoption of neural ODEs. In this paper, we propose an approach based on single-step implicit schemes to enable neural ODEs to handle stiffness and demonstrate that our implicit neural ODE method can learn stiff dynamics. This work addresses a key limitation in current neural ODE methods, paving the way for their use in a wider range of scientific problems.
title Training Stiff Neural Ordinary Differential Equations with Implicit Single-Step Methods
topic Numerical Analysis
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2410.05592