Bonn 2025 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
Q: Fachverband Quantenoptik und Photonik
Q 63: Poster – Quantum Information (joint session QI/Q)
Q 63.10: Poster
Donnerstag, 13. März 2025, 17:00–19:00, Tent
Quantum vs. classical: A comprehensive benchmark study for time series prediction using variational quantum algorithms — •Tobias Fellner1, David Kreplin2, Samuel Tovey1, and Christian Holm1 — 1Institute for Computational Physics, University of Stuttgart — 2Fraunhofer Institute for Manufacturing Engineering and Automation (IPA)
Recently, a wide range of variational quantum algorithms have been proposed for time series processing, promising potential advantages in handling complex sequential data. However, whether and how these quantum machine learning models outperform established classical approaches remains unclear. In this work, we conduct a comprehensive benchmark study comparing a variety of classical machine learning models and variational quantum algorithms for time series prediction. We evaluate their performance on time series prediction tasks of chaotic systems of varying complexity. Our results show that in many cases quantum machine learning models are able to achieve prediction accuracies comparable to classical models. At the same time, we also discuss the current practical value as well as the limitations of variational quantum algorithms for time series forecasting.
Keywords: variational quantum algorithms; time series prediction; benchmark