EUVIMEDEUVIMED entdecken
Crossref

Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization

Yabo Wang, Bo Qi, Chris Ferrie, Daoyi Dong

Physical Review Applied · 04.11.2024 · 22 (5)

DOI: 10.1103/physrevapplied.22.054005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review Applied, online erschienen am 04.11.2024. Verfasst von Yabo Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Australian Research Council’s.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Parameterized quantum circuits (PQCs) have been widely used as a machine learning model to explore the potential of achieving quantum advantages for various tasks. However, training PQCs is notoriously challenging owing to the phenomenon of plateaus and/or the existence of (exponentially) many spurious local minima. To enhance trainability, in this work we propose an efficient parameter initialization strategy with theoretical guarantees. We prove that by reducing the initial domain of each parameter inversely proportional to the square root of circuit depth, the magnitude of the cost gradient decays at most polynomially with respect to qubit count and circuit depth. Our theoretical results are substantiated through numerical simulations of variational quantum eigensolver tasks. Moreover, we demonstrate that the reduced-domain initialization strategy can protect specific quantum neural networks from exponentially many spurious local minima. Our results highlight the significance of an appropriate parameter initialization strategy, offering insights to enhance the trainability and convergence of variational quantum algorithms.

Förderung

  • National Natural Science Foundation of China
  • Australian Research Council’s

Zitieren

APA

Wang, Y., Qi, B., Ferrie, C., & Dong, D. (2024). Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization. Physical Review Applied, 22(5). https://doi.org/10.1103/physrevapplied.22.054005

Vancouver

Wang Y, Qi B, Ferrie C, Dong D. Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization. Physical Review Applied. 2024;22(5). doi:10.1103/physrevapplied.22.054005

BibTeX
@article{Wang2024,
  author = {Wang, Yabo and Qi, Bo and Ferrie, Chris and Dong, Daoyi},
  title = {Trainability enhancement of parameterized quantum circuits via reduced-domain parameter initialization},
  journal = {Physical Review Applied},
  year = {2024},
  volume = {22},
  number = {5},
  doi = {10.1103/physrevapplied.22.054005}
}
Kostenlos starten →