English

Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics

Optimization and Control 2024-02-19 v1 Computational Physics

Abstract

We propose Gauss-Newton's method in function space for the solution of the Navier-Stokes equations in the physics-informed neural network (PINN) framework. Upon discretization, this yields a natural gradient method that provably mimics the function space dynamics. Our computational results demonstrate close to single-precision accuracy measured in relative L2L^2 norm on a number of benchmark problems. To the best of our knowledge, this constitutes the first contribution in the PINN literature that solves the Navier-Stokes equations to this degree of accuracy. Finally, we show that given a suitable integral discretization, the proposed optimization algorithm agrees with Gauss-Newton's method in parameter space. This allows a matrix-free formulation enabling efficient scalability to large network sizes.

Keywords

Cite

@article{arxiv.2402.10680,
  title  = {Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics},
  author = {Anas Jnini and Flavio Vella and Marius Zeinhofer},
  journal= {arXiv preprint arXiv:2402.10680},
  year   = {2024}
}
R2 v1 2026-06-28T14:50:42.647Z