EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Relaxation-assisted reverse annealing on nonnegative/binary matrix factorization

Renichiro Haba iD, Masayuki Ohzeki, Kazuyuki Tanaka

PLOS One · 2025

DOI: 10.1371/journal.pone.0323232 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Renichiro Haba und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Information Sciences, Tohoku University, Sendai, Japan. Hauptthemen laut MEDLINE: Algorithms. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cabinet Office, Government of Japan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantum annealing has garnered significant attention as meta-heuristics inspired by quantum physics for combinatorial optimization problems. Among its many applications, nonnegative/binary matrix factorization stands out for its complexity and relevance in unsupervised machine learning. The use of reverse annealing, a derivative procedure of quantum annealing to prioritize the search in a vicinity under a given initial state, helps improve its optimization performance in matrix factorization. This study proposes an improved strategy that integrates reverse annealing with a linear programming relaxation technique. Using relaxed solutions as the initial configuration for reverse annealing, we demonstrate improvements in optimization performance comparable to the exact optimization methods. Our experiments on facial image datasets show that our method provides better convergence than known reverse annealing methods. Furthermore, we investigate the effectiveness of relaxation-based initialization methods on randomized datasets, demonstrating a relationship between the relaxed solution and the optimal solution. This research underscores the potential of combining reverse annealing and classical optimization strategies to enhance optimization performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsHumansFaceMachine LearningQuantum Theory

Autor:innen und Institutionen

  • Graduate School of Information Sciences, Tohoku University, Sendai, Japan.
  • Sigma-i Co. Ltd., Tokyo, Japan.
  • Department of Physics, Institute of Science Tokyo, Tokyo, Japan.

ORCID-Profile: Renichiro Haba

Förderung

  • Cabinet Office, Government of Japan

Zitieren

APA

Haba, R., Ohzeki, M., & Tanaka, K. (2025). Relaxation-assisted reverse annealing on nonnegative/binary matrix factorization. PLOS One. https://doi.org/10.1371/journal.pone.0323232

Vancouver

Haba R, Ohzeki M, Tanaka K. Relaxation-assisted reverse annealing on nonnegative/binary matrix factorization. PLOS One. 2025. doi:10.1371/journal.pone.0323232

BibTeX
@article{Haba2025,
  author = {Haba, Renichiro and Ohzeki, Masayuki and Tanaka, Kazuyuki},
  title = {Relaxation-assisted reverse annealing on nonnegative/binary matrix factorization},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0323232}
}
Kostenlos starten →