English

Stability Margins of Neural Network Controllers

Systems and Control 2026-01-16 v1 Systems and Control

Abstract

We present a method to train neural network controllers with guaranteed stability margins. The method is applicable to linear time-invariant plants interconnected with uncertainties and nonlinearities that are described by integral quadratic constraints. The type of stability margin we consider is the disk margin. Our training method alternates between a training step to maximize reward and a stability margin-enforcing step. In the stability margin enforcing-step, we solve a semidefinite program to project the controller into the set of controllers for which we can certify the desired disk margin.

Keywords

Cite

@article{arxiv.2409.09184,
  title  = {Stability Margins of Neural Network Controllers},
  author = {Neelay Junnarkar and Murat Arcak and Peter Seiler},
  journal= {arXiv preprint arXiv:2409.09184},
  year   = {2026}
}
R2 v1 2026-06-28T18:44:20.385Z