Random Neural Network Expressivity for Non-Linear Partial Differential Equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mehmood, Muhammed Ali, Gonon, Lukas
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914597750964224
author Mehmood, Muhammed Ali
Gonon, Lukas
author_facet Mehmood, Muhammed Ali
Gonon, Lukas
contents Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we study RaNN expressivity for learning solutions to non-linear partial differential equations (PDEs). Despite their widespread use in practical applications, a rigorous theoretical understanding of the approximation properties of RaNNs in this context remains limited. Here, we derive error bounds for RaNN approximations to time-dependent Sobolev functions and obtain a dimension-free approximation rate $\frac{1}{2}$ for sufficiently regular functions. We apply our results to two important classes of non-linear PDEs: Porous Medium Equations and Compressible Navier-Stokes Equations, showing that RaNNs are capable of efficiently approximating solutions to these complex, non-linear PDEs. Our theoretical analysis is supported by numerical experiments, showing that the obtained convergence rates extend beyond the considered setting.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25057
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Random Neural Network Expressivity for Non-Linear Partial Differential Equations
Mehmood, Muhammed Ali
Gonon, Lukas
Numerical Analysis
Machine Learning
Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we study RaNN expressivity for learning solutions to non-linear partial differential equations (PDEs). Despite their widespread use in practical applications, a rigorous theoretical understanding of the approximation properties of RaNNs in this context remains limited. Here, we derive error bounds for RaNN approximations to time-dependent Sobolev functions and obtain a dimension-free approximation rate $\frac{1}{2}$ for sufficiently regular functions. We apply our results to two important classes of non-linear PDEs: Porous Medium Equations and Compressible Navier-Stokes Equations, showing that RaNNs are capable of efficiently approximating solutions to these complex, non-linear PDEs. Our theoretical analysis is supported by numerical experiments, showing that the obtained convergence rates extend beyond the considered setting.
title Random Neural Network Expressivity for Non-Linear Partial Differential Equations
topic Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2605.25057