Stability Analysis of a B-Spline Deep Neural Operator for Nonlinear Systems
Abstract
This paper investigates the stability properties of neural operators through the structured representation offered by the Hybrid B-spline Deep Neural Operator (HBDNO). While existing stability-aware architectures typically enforce restrictive constraints that limit universality, HBDNO preserves full expressive power by representing outputs via B-spline control points. We show that these control points form a natural observable for post-training stability analysis. By applying Dynamic Mode Decomposition and connecting the resulting discrete dynamics to the Koopman operator framework, we provide a principled approach to spectral characterization of learned operators. Numerical results demonstrate the ability to assess stability and reveal future directions for safety-critical applications.
Cite
@article{arxiv.2512.19291,
title = {Stability Analysis of a B-Spline Deep Neural Operator for Nonlinear Systems},
author = {Raffaele Romagnoli and Soummya Kar},
journal= {arXiv preprint arXiv:2512.19291},
year = {2025}
}