Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods
Quantum Reports · 31.07.2026 · 8 (3) · 73
DOI: 10.3390/quantum8030073 ↗Kurz gefasst
Fachartikel in der Zeitschrift Quantum Reports, online erschienen am 31.07.2026. Verfasst von Demerson N. Gonçalves und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Brazilian Ministry of Defense, Financiadora de Estudos e Projetos.
Abstract (Originalsprache)
The minimum accuracy heuristic provides a training-free way to evaluate quantum feature maps, but its original formulation assumes balanced datasets, requires an exhaustive Pauli-axis scan, and lacks a formal lower-bound interpretation. In this work, we generalize the metric to arbitrary binary datasets and prove that the resulting generalized minimum accuracy, denoted Rmin, is a certified lower bound on the optimal empirical accuracy R* achievable by linear classifiers in the same feature space. To improve scalability, we introduce Monte Carlo axis-selection strategies that estimate Rmin from random subsets of Pauli-feature axes and derive quantile-coverage guarantees for sampling high-accuracy directions. We validate the framework using exact statevector simulations of an n=6 qubit quantum feature map, corresponding to d=46=4096 Pauli axes, over 30 independent runs on five synthetic datasets. The proposed methods sample as few as 60 axes, produce lower-bound estimates and achieve speedups of approximately 27× to 68× compared with exhaustive evaluation. The results support generalized minimum accuracy as a scalable and theoretically grounded tool for pre-screening quantum feature maps in simulated quantum-kernel workflows.
Förderung
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Brazilian Ministry of Defense
- Financiadora de Estudos e Projetos
Zitieren
APA
Gonçalves, D. N., Fernandes, T. D., Cordeiro, A. M. M., Lugao, P. H. G., Dias, J. T., & Moreira, F. M. A. (2026). Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods. Quantum Reports, 8(3), 73. https://doi.org/10.3390/quantum8030073
Vancouver
Gonçalves DN, Fernandes TD, Cordeiro AMM, Lugao PHG, Dias JT, Moreira FMA. Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods. Quantum Reports. 2026;8(3):73. doi:10.3390/quantum8030073
BibTeX
@article{Gonalves2026,
author = {Gonçalves, Demerson N. and Fernandes, Tharso D. and Cordeiro, Andrias M. M. and Lugao, Pedro H. G. and Dias, João T. and Moreira, Fernando M. Araújo},
title = {Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods},
journal = {Quantum Reports},
year = {2026},
volume = {8},
number = {3},
pages = {73},
doi = {10.3390/quantum8030073}
}
EUVIMED