BACK TO INDEX

Publications of Eduardo D. Sontag jointly with I.R. Manchester
Conference articles
  1. A. C. B. de Oliveira, R. Wang, I.R. Manchester, and E. D. Sontag. Remarks on Lipschitz-minimal interpolation: Generalization bounds and neural network implementation. In Proc. 65th IEEE Conference on Decision and Control (CDC), 2026. Note: Submitted. Also arXiv:2603.19524.
    Abstract:
    This note establishes a theoretical framework for finding (potentially overparameterized) approximations of a function on a compact set with a-priori bounds for the generalization error. The approximation method considered is to choose, among all functions that (approximately) interpolate a given data set, one with a minimal Lipschitz constant. The paper establishes rigorous generalization bounds over practically relevant classes of approximators, including deep neural networks. It also presents a neural network implementation based on Lipschitz-bounded network layers and an augmented Lagrangian method. The results are illustrated for a problem of learning the dynamics of an input-to-state stable system with certified bounds on simulation error.



BACK TO INDEX




Disclaimer:

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders.




Last modified: Sun Apr 12 22:21:34 2026
Author: sontag.


This document was translated from BibTEX by bibtex2html