A finite-sample generalization bound for stable LPV systems
Mathematics of Control, Signals, and Systems · 2026-06 · 38 (2) · 241-273
DOI: 10.1007/s00498-025-00427-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics of Control, Signals, and Systems, online erschienen am 08.04.2026. Verfasst von Dániel Rácz und 4 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mesterséges Intelligencia Nemzeti Laboratórium, C.N.R.S. E.A.I., European Defence Fund.
Abstract (Originalsprache)
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.
Förderung
- Mesterséges Intelligencia Nemzeti Laboratórium
- C.N.R.S. E.A.I.
- European Defence Fund
- HUN-REN Institute for Computer Science and Control
Zitieren
APA
Rácz, D., Gonzalez, M., Petreczky, M., Benczúr, A., & Daróczy, B. (2026). A finite-sample generalization bound for stable LPV systems. Mathematics of Control, Signals, and Systems, 38(2), 241-273. https://doi.org/10.1007/s00498-025-00427-7
Vancouver
Rácz D, Gonzalez M, Petreczky M, Benczúr A, Daróczy B. A finite-sample generalization bound for stable LPV systems. Mathematics of Control, Signals, and Systems. 2026;38(2):241-273. doi:10.1007/s00498-025-00427-7
BibTeX
@article{Rcz2026,
author = {Rácz, Dániel and Gonzalez, Martin and Petreczky, Mihály and Benczúr, András and Daróczy, Bálint},
title = {A finite-sample generalization bound for stable LPV systems},
journal = {Mathematics of Control, Signals, and Systems},
year = {2026},
volume = {38},
number = {2},
pages = {241--273},
doi = {10.1007/s00498-025-00427-7}
}
EUVIMED