Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learning

Xiaobing Dai, Armin Lederer, Zewen Yang, Sandra Hirche

Publikation: Beitrag in FachzeitschriftKonferenzartikelBegutachtung

10 Zitate (Scopus)

Abstract

When the dynamics of systems are unknown, supervised machine learning techniques are commonly employed to infer models from data. Gaussian process (GP) regression is a particularly popular learning method for this purpose due to the existence of prediction error bounds. Moreover, GP models can be efficiently updated online, such that event-triggered online learning strategies can be pursued to ensure specified tracking accuracies. However, existing trigger conditions must be able to be evaluated at arbitrary times, which cannot be achieved in practice due to non-negligible computation times. Therefore, we first derive a delay-aware tracking error bound, which reveals an accuracy-delay trade-off. Based on this result, we propose a novel event trigger for GP-based online learning with computational delays, which we show to offer advantages over offline trained GP models for sufficiently small computation times. Finally, we demonstrate the effectiveness of the proposed event trigger for online learning in simulations.

OriginalspracheEnglisch
Seiten (von - bis)445-457
Seitenumfang13
FachzeitschriftProceedings of Machine Learning Research
Jahrgang211
PublikationsstatusVeröffentlicht - 2023
Veranstaltung5th Annual Conference on Learning for Dynamics and Control, L4DC 2023 - Philadelphia, USA/Vereinigte Staaten
Dauer: 15 Juni 202316 Juni 2023

Fingerprint

Untersuchen Sie die Forschungsthemen von „Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learning“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren