English

A finite-sample generalization bound for stable LPV systems

Machine Learning 2024-05-22 v3 Systems and Control Systems and Control

Abstract

One of the main theoretical challenges in learning dynamical systems from data is providing upper bounds on the generalization error, that is, the difference between the expected prediction error and the empirical prediction error measured on some finite sample. In machine learning, a popular class of such bounds are the so-called Probably Approximately Correct (PAC) bounds. In this paper, we derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered.

Keywords

Cite

@article{arxiv.2405.10054,
  title  = {A finite-sample generalization bound for stable LPV systems},
  author = {Daniel Racz and Martin Gonzalez and Mihaly Petreczky and Andras Benczur and Balint Daroczy},
  journal= {arXiv preprint arXiv:2405.10054},
  year   = {2024}
}

Comments

8 pages, 1 figure, under review

R2 v1 2026-06-28T16:29:27.517Z