Linear Stability Analysis of Physics-Informed Random Projection Neural Networks for ODEs
This work addresses the problem of solving stiff ODEs for computational scientists and engineers, offering a novel neural network-based approach with theoretical guarantees, though it appears incremental as it builds on existing physics-informed neural network methods.
The paper tackles the numerical solution of stiff ordinary differential equations (ODEs) by analyzing the linear stability of physics-informed random projection neural networks (PI-RPNNs), proving they are uniform approximators and provide consistent, asymptotically stable, and convergent schemes, with numerical comparisons to methods like backward Euler and Radau schemes.
We present a linear stability analysis of physics-informed random projection neural networks (PI-RPNNs), for the numerical solution of {the initial value problem (IVP)} of (stiff) ODEs. We begin by proving that PI-RPNNs are uniform approximators of the solution to ODEs. We then provide a constructive proof demonstrating that PI-RPNNs offer consistent and asymptotically stable numerical schemes, thus convergent schemes. In particular, we prove that multi-collocation PI-RPNNs guarantee asymptotic stability. Our theoretical results are illustrated via numerical solutions of benchmark examples including indicative comparisons with the backward Euler method, the midpoint method, the trapezoidal rule, the 2-stage Gauss scheme, and the 2- and 3-stage Radau schemes.