EUVIMEDEUVIMED entdecken
Crossref

Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding

Taiga Hayashi, Yuya Seki, Kotaro Terada, Yosuke Mukasa, Shuta Kikuchi, Shu Tanaka

Journal of the Physical Society of Japan · 15.12.2026 · 95 (12)

DOI: 10.7566/jpsj.95.124005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Physical Society of Japan, erschienen am 15.12.2026. Verfasst von Taiga Hayashi und 5 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science, Japan Science and Technology Agency.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Factorization machine with quadratic-optimization annealing (FMQA) is a black-box optimization method that combines a factorization machine (FM) surrogate with search based on quadratic unconstrained binary optimization (QUBO) by an Ising machine. When FMQA is applied to integer or discretized continuous variables via one-hot encoding, uniform random initial sampling can leave many binary variables never active in the initial training data, and the corresponding FM parameters receive no direct gradient updates from the observed responses. We address this by designing the initial training data to achieve complete marginal bit coverage, namely, ensuring that every binary variable obtained by one-hot encoding takes the value one at least once. We use two space-filling sampling methods, Latin hypercube sampling (LHS) and the Sobol’ sequence, yielding LHS-FMQA and Sobol’-FMQA. On the human-powered aircraft wing-shape optimization benchmark with 17 and 32 design variables, both proposed methods achieved numerically higher mean final cruising speeds than the baseline FMQA, with the advantage more pronounced on the 32-variable problem.

Förderung

  • Japan Society for the Promotion of Science
  • Japan Science and Technology Agency

Zitieren

APA

Hayashi, T., Seki, Y., Terada, K., Mukasa, Y., Kikuchi, S., & Tanaka, S. (2026). Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding. Journal of the Physical Society of Japan, 95(12). https://doi.org/10.7566/jpsj.95.124005

Vancouver

Hayashi T, Seki Y, Terada K, Mukasa Y, Kikuchi S, Tanaka S. Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding. Journal of the Physical Society of Japan. 2026;95(12). doi:10.7566/jpsj.95.124005

BibTeX
@article{Hayashi2026,
  author = {Hayashi, Taiga and Seki, Yuya and Terada, Kotaro and Mukasa, Yosuke and Kikuchi, Shuta and Tanaka, Shu},
  title = {Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding},
  journal = {Journal of the Physical Society of Japan},
  year = {2026},
  volume = {95},
  number = {12},
  doi = {10.7566/jpsj.95.124005}
}
Kostenlos starten →