R.I.P.
๐ป
Ghosted
Random Neural Network Expressivity for Non-Linear Partial Differential Equations
May 24, 2026 ยท Grace Period ยท + Add venue
Authors
Muhammed Ali Mehmood, Lukas Gonon
arXiv ID
2605.25057
Category
math.NA: Numerical Analysis
Cross-listed
cs.LG
Citations
0
Abstract
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.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Numerical Analysis
R.I.P.
๐ป
Ghosted
Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
R.I.P.
๐ป
Ghosted
PDE-Net: Learning PDEs from Data
R.I.P.
๐ป
Ghosted
Efficient tensor completion for color image and video recovery: Low-rank tensor train
R.I.P.
๐ป
Ghosted
Tensor Ring Decomposition
R.I.P.
๐ป
Ghosted