Stability of neural ODEs by a control over the expansivity of their flows

Abstract

We propose a method to enhance the stability of a neural ordinary differential equation (neural ODE) by means of a control over the Lipschitz constant $C$ of its flow. Since it is known that $C$ depends on the logarithmic norm of the Jacobian matrix associated with the neural ODE, we tune this parameter at our convenience by suitably perturbing the Jacobian matrix with a perturbation as small as possible in Frobenius norm. We do so by introducing an optimization problem for which we propose a nested two-level algorithm. For a given perturbation size, the inner level computes the optimal perturbation with a fixed Frobenius norm, while the outer level tunes the perturbation amplitude. We embed the proposed algorithm in the training of the neural ODE to improve its stability. Numerical experiments on the MNIST and FashionMNIST datasets show that an image classifier including a neural ODE in its architecture trained according to our strategy is more stable than the same classifier trained in the classical way, and therefore, it is more robust and less vulnerable to adversarial attacks.

Please cite this paper as:

@article{demarinis2025stability,
  title={Stability of neural ODEs by a control over the expansivity of their
  flows},
  author={De Marinis, Arturo and Guglielmi, Nicola and  Sicilia, Stefano and Tudisco, Francesco},
  journal={arXiv:2501.10740},
  year={2025}
}

Keywords: neural ode deep learning neural networks adversarial attacks nonlinear eigenvalues eigenvalue optimization