Remarks on Lipschitz-Minimal Interpolation: Generalization Bounds and Neural Network Implementation
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.
Cite
@article{arxiv.2603.19524,
title = {Remarks on Lipschitz-Minimal Interpolation: Generalization Bounds and Neural Network Implementation},
author = {Arthur C. B. de Oliveira and Ruigang Wang and Ian R. Manchester and Eduardo D. Sontag},
journal= {arXiv preprint arXiv:2603.19524},
year = {2026}
}
Comments
9 pages, 3 figures, 3 tables