Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits

Kölle, Michael; Feist, Alexander; Stein, Jonas und Linnhoff-Popien, Claudia (Juli 2025): Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits. ICCS 2025: 25th International Conference on Computational Science, Singapore, Singapore, 07. Juli 2025 - 09. Juli 2025. Lees, Michael H.; Cai, Wentong; Cheong, Siew Ann; Su, Yi; Abramson, David; Dongarra, Jack J. und Sloot, Peter M. A. (Hrsg.): In: Computational Science — ICCS : 25th International Conference, Singapore, Singapore, July 7–9, 2025, Proceedings, Cham: Springer. S. 275-282

Abstract

In recent years, neural networks (NNs) have driven significant advances in machine learning. However, as tasks grow more complex, NNs often require large numbers of trainable parameters, which increases computational and energy demands. Variational quantum circuits (VQCs) offer a promising alternative: they leverage quantum mechanics to capture intricate relationships and typically need fewer parameters. In this work, we evaluate NNs and VQCs on simple supervised and reinforcement learning tasks, examining models with different parameter sizes. We simulate VQCs and execute selected parts of the training process on real quantum hardware to approximate actual training times. Our results show that VQCs can match NNs in performance while using significantly fewer parameters, despite longer training durations. As quantum technology and algorithms advance, and VQC architectures improve, we posit that VQCs could become advantageous for certain machine learning tasks.

• Dokumententyp: Konferenzbeitrag (Paper)
• Keywords: toappear
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 978-3-031-97635-3
• Ort: Cham
• Sprache: Englisch