Saved in:
Bibliographic Details
Main Author: Chaudhry, Faris
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.12556
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912964529881088
author Chaudhry, Faris
author_facet Chaudhry, Faris
contents We establish empirical scaling laws for Single-Layer Physics-Informed Neural Networks on canonical nonlinear PDEs. We identify a dual optimization failure: (i) a baseline pathology, where the solution error fails to decrease with network width, even at fixed nonlinearity, falling short of theoretical approximation bounds, and (ii) a compounding pathology, where this failure is exacerbated by nonlinearity. We provide quantitative evidence that a simple separable power law is insufficient, and that the scaling behavior is governed by a more complex, non-separable relationship. This failure is consistent with the concept of spectral bias, where networks struggle to learn the high-frequency solution components that intensify with nonlinearity. We show that optimization, not approximation capacity, is the primary bottleneck, and propose a methodology to empirically measure these complex scaling effects.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12556
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scaling Laws and Pathologies of Single-Layer PINNs: Network Width and PDE Nonlinearity
Chaudhry, Faris
Machine Learning
Numerical Analysis
Computational Physics
We establish empirical scaling laws for Single-Layer Physics-Informed Neural Networks on canonical nonlinear PDEs. We identify a dual optimization failure: (i) a baseline pathology, where the solution error fails to decrease with network width, even at fixed nonlinearity, falling short of theoretical approximation bounds, and (ii) a compounding pathology, where this failure is exacerbated by nonlinearity. We provide quantitative evidence that a simple separable power law is insufficient, and that the scaling behavior is governed by a more complex, non-separable relationship. This failure is consistent with the concept of spectral bias, where networks struggle to learn the high-frequency solution components that intensify with nonlinearity. We show that optimization, not approximation capacity, is the primary bottleneck, and propose a methodology to empirically measure these complex scaling effects.
title Scaling Laws and Pathologies of Single-Layer PINNs: Network Width and PDE Nonlinearity
topic Machine Learning
Numerical Analysis
Computational Physics
url https://arxiv.org/abs/2603.12556