Quantifying the effect of quantum operations in machine learning by comparison to classically simulable variants

Luque, Víctor Mauricio Gutiérrez; Berta, Mario Andrea; Stutte, Benjamin; Unruh, Dominique

doi:10.18154/RWTH-2026-06388

Quantifying the effect of quantum operations in machine learning by comparison to classically simulable variants

Luque, Víctor Mauricio Gutiérrez^RWTH*

2026

VerantwortlichkeitsangabeVíctor Mauricio Gutiérrez Luque

ImpressumAachen : RWTH Aachen University 2026

Umfang1 Online-Ressource : Illustrationen

Bachelorarbeit, RWTH Aachen University, 2026

Veröffentlicht auf dem Publikationsserver der RWTH Aachen University

Genehmigende Fakultät
Fak09

Hauptberichter/Gutachter
Unruh, Dominique (Thesis advisor)^RWTH* ; Berta, Mario Andrea (Thesis advisor)^RWTH* ; Stutte, Benjamin (Consultant)^RWTH*

Tag der mündlichen Prüfung/Habilitation
2026-05-12

Online
DOI: 10.18154/RWTH-2026-06388
URL: https://publications.rwth-aachen.de/record/1038237/files/1038237.pdf

Einrichtungen

Lehrstuhl für Quanteninformationssysteme (Informatik 15) (125910)

Thematische Einordnung (Klassifikation)
DDC: 004

Kurzfassung
Quantum machine learning (QML) investigates whether quantum-mechanical representations and computations can improve machine-learning tasks. However, it is often unclear which observed performance differences are genuinely attributable to specifically quantum features rather than to architectural differences that can be implemented classically or benchmarking effects. This thesis studies the role of entanglement in variational QML models through a controlled ablation or removal framework. The work introduces partially and fully separable variants of the Circuit-centric Classifier (CCC) and IQP-Kernel Classifier, constructed by systematically reducing entangling interactions while keeping the remaining training and evaluation pipeline fixed. The models are evaluated on multiple synthetic and structured benchmark families, including but not limited to linearly separable, hidden-manifold, and hyperplane-based datasets. The results show that partially entangling variants often remain competitive with the original models, whereas fully separable variants typically exhibit larger performance degradation. The experiments are consistent with entanglement contributing meaningfully to performance in the studied models, while also suggesting that sparse entangling connectivity may already retain much of the observed benefit of the original architectures in this benchmark setting. The IQP-kernel experiments scaled prohibitively in higher-dimensional settings, exceeding the available computational budget.

OpenAccess:
PDF