English

Stability Analysis of a B-Spline Deep Neural Operator for Nonlinear Systems

Systems and Control 2025-12-23 v1 Systems and Control

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.

Keywords

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}
}
R2 v1 2026-07-01T08:36:43.932Z