Physics Informed Random Feature Neural Networks for Solving PDEs
math.NA, cs.LG, cs.NA
Submitted: 2026-09-14
Updated: 2026-09-14
Project page: https://liaochunyang.github.io
License: http://creativecommons.org/licenses/by/4.0/
The gist: Machine learning-based partial differential equations (PDEs) solvers have attracted significant attention in recent years.
Terminology
Abstract
Machine learning-based partial differential equations (PDEs) solvers have attracted significant attention in recent years. Most progress in this area has been driven by deep neural networks such as physics-informed neural networks (PINNs) and kernel method (such as physics-informed Gaussian Processes). We introduce a physics-informed random feature method for countering part of the spectral bias which PINN-based solvers are facing for a certain class of PDEs. Random feature method was originally proposed to approximate large-scale kernel machines and can be viewed as a specialized randomized neural network. Compared to other state-of-the-art PINN-based solvers which require a large number of collocation points, our proposed method reduces the computational complexity. In this paper, we develop a rigorous approximation error analysis and derive high-probability error bounds on the H 1 norm. We provide extensive numerical tests for verifying our theoretical guarantees on error decay rates, as well as several comparison tests to showcase our claimed capability for combating spectral bias in these deep learning based methods.
Sources
- Convergence and error control of consistent PINNs for elliptic PDEs
- Cauchy Random Features for Operator Learning in Sobolev Space
- Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
- Data-efficient Kernel Methods for Learning Hamiltonian Systems
- Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems