Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates
This work addresses a domain-specific problem in computational fluid dynamics and numerical analysis, providing incremental improvements in approximation methods for divergence-free fields.
The paper tackles the problem of approximating divergence-free vector fields using linearized shallow neural networks, achieving optimal approximation rates under an exact divergence-free constraint, as confirmed by numerical experiments in two and three dimensions.
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$^k$ networks, we derive a core integral representation of divergence-free Sobolev vector fields through antisymmetric potentials parameterized by linearized ReLU$^k$ neural networks. This representation, together with a quasi-uniform distribution argument for the inner parameters, yields optimal approximation rates for such linearized ReLU$^k$ neural networks under an exact divergence-free constraint. Numerical experiments in two and three spatial dimensions, including $L^2$ projection and steady Stokes problems, confirm the theoretical rates and illustrate the effectiveness of exactly divergence-free conditions in computation.