Rácz, Dániel and Gonzalez, Martin and Petreczky, Mihály and Benczúr, András, ifj and Daróczy, Bálint Zoltán (2026) A finite-sample generalization bound for stable LPV systems. MATHEMATICS OF CONTROL SIGNALS AND SYSTEMS, 2026. pp. 1-33. ISSN 0932-4194 10.1007/s00498-025-00427-7

Text Racz_1_37067599_ny.pdf Download (593kB)

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 a weighted \text { H}_{\text { 2}} H 2 -like norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered.

Item Type:	Article
Subjects:	Q Science > QA Mathematics and Computer Science > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Divisions:	Artificial Intelligence Laboratory
SWORD Depositor:	MTMT Injector
Depositing User:	MTMT Injector
Date Deposited:	03 Jun 2026 07:21
Last Modified:	03 Jun 2026 07:21
URI:	https://eprints.sztaki.hu/id/eprint/11127

Update Item