A hyperparameter study for quantum kernel methods
Quantum Machine Intelligence · 2024-12 · 6 (2)
DOI: 10.1007/s42484-024-00172-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Quantum Machine Intelligence, online erschienen am 15.07.2024. Verfasst von Sebastian Egginger und 2 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fraunhofer-Institut für Kognitive Systeme IKS.
Abstract (Originalsprache)
Quantum kernel methods are a promising method in quantum machine learning thanks to the guarantees connected to them. Their accessibility for analytic considerations also opens up the possibility of prescreening datasets based on their potential for a quantum advantage. To do so, earlier works developed the geometric difference, which can be understood as a closeness measure between two kernel-based machine learning approaches, most importantly between a quantum kernel and a classical kernel. This metric links the quantum and classical model complexities, and it was developed to bound generalization error. Therefore, it raises the question of how this metric behaves in an empirical setting. In this work, we investigate the effects of hyperparameter choice on the model performance and the generalization gap between classical and quantum kernels. The importance of hyperparameters is well known also for classical machine learning. Of special interest are hyperparameters associated with the quantum Hamiltonian evolution feature map, as well as the number of qubits to trace out before computing a projected quantum kernel. We conduct a thorough investigation of the hyperparameters across 11 datasets, and we identify certain aspects that can be exploited. Analyzing the effects of certain hyperparameter settings on the empirical performance, as measured by cross validation accuracy, and generalization ability, as measured by geometric difference described above, brings us one step closer to understanding the potential of quantum kernel methods on classical datasets.
Förderung
- Fraunhofer-Institut für Kognitive Systeme IKS
Zitieren
APA
Egginger, S., Sakhnenko, A., & Lorenz, J. M. (2024). A hyperparameter study for quantum kernel methods. Quantum Machine Intelligence, 6(2). https://doi.org/10.1007/s42484-024-00172-1
Vancouver
Egginger S, Sakhnenko A, Lorenz JM. A hyperparameter study for quantum kernel methods. Quantum Machine Intelligence. 2024;6(2). doi:10.1007/s42484-024-00172-1
BibTeX
@article{Egginger2024,
author = {Egginger, Sebastian and Sakhnenko, Alona and Lorenz, Jeanette Miriam},
title = {A hyperparameter study for quantum kernel methods},
journal = {Quantum Machine Intelligence},
year = {2024},
volume = {6},
number = {2},
doi = {10.1007/s42484-024-00172-1}
}
EUVIMED