Solving Differential Equations using Physics-Informed Deep Equilibrium Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pacheco, Bruno Machado, Camponogara, Eduardo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914851126771712
author Pacheco, Bruno Machado
Camponogara, Eduardo
author_facet Pacheco, Bruno Machado
Camponogara, Eduardo
contents This paper introduces Physics-Informed Deep Equilibrium Models (PIDEQs) for solving initial value problems (IVPs) of ordinary differential equations (ODEs). Leveraging recent advancements in deep equilibrium models (DEQs) and physics-informed neural networks (PINNs), PIDEQs combine the implicit output representation of DEQs with physics-informed training techniques. We validate PIDEQs using the Van der Pol oscillator as a benchmark problem, demonstrating their efficiency and effectiveness in solving IVPs. Our analysis includes key hyperparameter considerations for optimizing PIDEQ performance. By bridging deep learning and physics-based modeling, this work advances computational techniques for solving IVPs, with implications for scientific computing and engineering applications.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03472
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Solving Differential Equations using Physics-Informed Deep Equilibrium Models
Pacheco, Bruno Machado
Camponogara, Eduardo
Machine Learning
Systems and Control
This paper introduces Physics-Informed Deep Equilibrium Models (PIDEQs) for solving initial value problems (IVPs) of ordinary differential equations (ODEs). Leveraging recent advancements in deep equilibrium models (DEQs) and physics-informed neural networks (PINNs), PIDEQs combine the implicit output representation of DEQs with physics-informed training techniques. We validate PIDEQs using the Van der Pol oscillator as a benchmark problem, demonstrating their efficiency and effectiveness in solving IVPs. Our analysis includes key hyperparameter considerations for optimizing PIDEQ performance. By bridging deep learning and physics-based modeling, this work advances computational techniques for solving IVPs, with implications for scientific computing and engineering applications.
title Solving Differential Equations using Physics-Informed Deep Equilibrium Models
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2406.03472