Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates
Abstract
This paper studies the numerical approximation of divergence-free vector fields by linearized shallow neural networks, also referred to as random feature models or finite neuron spaces. Combining the stable potential lifting for divergence-free fields with the scalar Sobolev integral representation theory via ReLU networks, we derive a core integral representation of divergence-free Sobolev vector fields through antisymmetric potentials parameterized by linearized ReLU neural networks. This representation, together with a quasi-uniform distribution argument for the inner parameters, yields optimal approximation rates for such linearized ReLU neural networks under an exact divergence-free constraint. Numerical experiments in two and three spatial dimensions, including projection and steady Stokes problems, confirm the theoretical rates and illustrate the effectiveness of exactly divergence-free conditions in computation.
Cite
@article{arxiv.2603.28638,
title = {Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates},
author = {Juncai He and Xinliang Liu and Zitong Tian},
journal= {arXiv preprint arXiv:2603.28638},
year = {2026}
}
Comments
27 pages, 11 figures