Dynamical scaling method improved by a deep learning approach

TL;DR

This paper introduces a deep learning-based dynamical scaling method that enhances accuracy and efficiency over traditional Gaussian process regression, especially for large datasets in statistical physics models.

Contribution

The authors develop a neural network approach that reduces computational costs and improves accuracy in dynamical scaling analysis for large datasets.

Findings

Achieved higher accuracy than conventional methods.

Significantly reduced computational cost.

Successfully applied to 2D Ising and Potts models.

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.