Linear Stability Analysis of Physics-Informed Random Projection Neural Networks for ODEs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fabiani, Gianluca, Bollt, Erik, Siettos, Constantinos, Yannacopoulos, Athanasios N.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913962949345280
author Fabiani, Gianluca
Bollt, Erik
Siettos, Constantinos
Yannacopoulos, Athanasios N.
author_facet Fabiani, Gianluca
Bollt, Erik
Siettos, Constantinos
Yannacopoulos, Athanasios N.
contents We present a linear stability analysis of physics-informed random projection neural networks (PI-RPNNs), for the numerical solution of {the initial value problem (IVP)} of (stiff) ODEs. We begin by proving that PI-RPNNs are uniform approximators of the solution to ODEs. We then provide a constructive proof demonstrating that PI-RPNNs offer consistent and asymptotically stable numerical schemes, thus convergent schemes. In particular, we prove that multi-collocation PI-RPNNs guarantee asymptotic stability. Our theoretical results are illustrated via numerical solutions of benchmark examples including indicative comparisons with the backward Euler method, the midpoint method, the trapezoidal rule, the 2-stage Gauss scheme, and the 2- and 3-stage Radau schemes.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15393
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Linear Stability Analysis of Physics-Informed Random Projection Neural Networks for ODEs
Fabiani, Gianluca
Bollt, Erik
Siettos, Constantinos
Yannacopoulos, Athanasios N.
Numerical Analysis
Machine Learning
Dynamical Systems
65L20, 68T07, 65L04, 37N30
We present a linear stability analysis of physics-informed random projection neural networks (PI-RPNNs), for the numerical solution of {the initial value problem (IVP)} of (stiff) ODEs. We begin by proving that PI-RPNNs are uniform approximators of the solution to ODEs. We then provide a constructive proof demonstrating that PI-RPNNs offer consistent and asymptotically stable numerical schemes, thus convergent schemes. In particular, we prove that multi-collocation PI-RPNNs guarantee asymptotic stability. Our theoretical results are illustrated via numerical solutions of benchmark examples including indicative comparisons with the backward Euler method, the midpoint method, the trapezoidal rule, the 2-stage Gauss scheme, and the 2- and 3-stage Radau schemes.
title Linear Stability Analysis of Physics-Informed Random Projection Neural Networks for ODEs
topic Numerical Analysis
Machine Learning
Dynamical Systems
65L20, 68T07, 65L04, 37N30
url https://arxiv.org/abs/2408.15393