Dynamical scaling method improved by a deep learning approach

Abstract

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.

References in corpus (6)

• Bayesian Inference in the Scaling Analysis of Critical Phenomena
• Finite spin-glass transition of the $\pm J$ XY model in three dimensions
• From measurements to inferences of physical quantities in numerical simulations
• A strategy for solving difficulties in spin-glass simulations
• Neural Network Approach to Scaling Analysis of Critical Phenomena
• Improvement of analysis for relaxation of fluctuations by the use of Gaussian process regression and extrapolation method