Saved in:
Bibliographic Details
Main Authors: de Oliveira, Arthur C. B., Wang, Ruigang, Manchester, Ian R., Sontag, Eduardo D.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19524
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915876398170112
author de Oliveira, Arthur C. B.
Wang, Ruigang
Manchester, Ian R.
Sontag, Eduardo D.
author_facet de Oliveira, Arthur C. B.
Wang, Ruigang
Manchester, Ian R.
Sontag, Eduardo D.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19524
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Remarks on Lipschitz-Minimal Interpolation: Generalization Bounds and Neural Network Implementation
de Oliveira, Arthur C. B.
Wang, Ruigang
Manchester, Ian R.
Sontag, Eduardo D.
Systems and Control
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.
title Remarks on Lipschitz-Minimal Interpolation: Generalization Bounds and Neural Network Implementation
topic Systems and Control
url https://arxiv.org/abs/2603.19524