English

Spectral-Bias and Kernel-Task Alignment in Physically Informed Neural Networks

Machine Learning 2023-10-09 v2 Disordered Systems and Neural Networks Machine Learning

Abstract

Physically informed neural networks (PINNs) are a promising emerging method for solving differential equations. As in many other deep learning approaches, the choice of PINN design and training protocol requires careful craftsmanship. Here, we suggest a comprehensive theoretical framework that sheds light on this important problem. Leveraging an equivalence between infinitely over-parameterized neural networks and Gaussian process regression (GPR), we derive an integro-differential equation that governs PINN prediction in the large data-set limit -- the neurally-informed equation. This equation augments the original one by a kernel term reflecting architecture choices and allows quantifying implicit bias induced by the network via a spectral decomposition of the source term in the original differential equation.

Keywords

Cite

@article{arxiv.2307.06362,
  title  = {Spectral-Bias and Kernel-Task Alignment in Physically Informed Neural Networks},
  author = {Inbar Seroussi and Asaf Miron and Zohar Ringel},
  journal= {arXiv preprint arXiv:2307.06362},
  year   = {2023}
}
R2 v1 2026-06-28T11:28:48.047Z