Dynamical Scaling Method Improved by a Deep Learning Approach
Journal of the Physical Society of Japan · 15.06.2026 · 95 (6)
DOI: 10.7566/jpsj.95.064004 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Physical Society of Japan, erschienen am 15.06.2026. Verfasst von Yusuke Terasawa und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Gefördert von: Japan Science and Technology Agency.
Abstract (Originalsprache)
We propose a dynamical scaling analysis improved by a deep learning approach. While Gaussian process regression has been widely employed for estimating scaling parameters, its computational cost for parameter optimization becomes a limitation in dynamical scaling analysis, where large datasets are involved. In contrast, the present method employs a neural network, which significantly reduces the computational cost and enables the use of the entire dataset that was inaccessible with Gaussian process regression. We applied the method to the 2D Ising model and the 2D 3-state Potts model, achieving higher accuracy and computational efficiency than conventional approaches.
Förderung
- Japan Science and Technology Agency
Zitieren
APA
Terasawa, Y., & Ozeki, Y. (2026). Dynamical Scaling Method Improved by a Deep Learning Approach. Journal of the Physical Society of Japan, 95(6). https://doi.org/10.7566/jpsj.95.064004
Vancouver
Terasawa Y, Ozeki Y. Dynamical Scaling Method Improved by a Deep Learning Approach. Journal of the Physical Society of Japan. 2026;95(6). doi:10.7566/jpsj.95.064004
BibTeX
@article{Terasawa2026,
author = {Terasawa, Yusuke and Ozeki, Yukiyasu},
title = {Dynamical Scaling Method Improved by a Deep Learning Approach},
journal = {Journal of the Physical Society of Japan},
year = {2026},
volume = {95},
number = {6},
doi = {10.7566/jpsj.95.064004}
}
EUVIMED