English

Unsupervised learning of topological phase transitions using Calinski-Harabaz index

Statistical Mechanics 2021-01-27 v1 Disordered Systems and Neural Networks

Abstract

Machine learning methods have been recently applied to learning phases of matter and transitions between them. Of particular interest is the topological phase transition, such as in the XY model, which can be difficult for unsupervised learning such as the principal component analysis. Recently, authors of [Nature Physics \textbf{15},790 (2019)] employed the diffusion-map method for identifying topological order and were able to determine the BKT phase transition of the XY model, specifically via the intersection of the average cluster distance Dˉ\bar{D} and the within cluster dispersion σˉ\bar\sigma (when the different clusters vary from separation to mixing together). However, sometimes it is not easy to find the intersection if Dˉ\bar{D} or σˉ\bar{\sigma} does not change too much due to topological constraint. In this paper, we propose to use the Calinski-Harabaz (chch) index, defined roughly as the ratio Dˉ/σˉ\bar D/\bar \sigma, to determine the critical points, at which the chch index reaches a maximum or minimum value, or jump sharply. We examine the chch index in several statistical models, including ones that contain a BKT phase transition. For the Ising model, the peaks of the quantity chch or its components are consistent with the position of the specific heat maximum. For the XY model both on the square lattices and honeycomb lattices, our results of the chch index show the convergence of the peaks over a range of the parameters ε/ε0\varepsilon/\varepsilon_0 in the Gaussian kernel. We also examine the generalized XY model with q=2q=2 and q=8q=8 and at the value away from the pure XY limit. Our method is thus useful to both topological and non-topological phase transitions and can achieve accuracy as good as supervised learning methods previously used in these models, and may be used for searching phases from experimental data.

Keywords

Cite

@article{arxiv.2010.06136,
  title  = {Unsupervised learning of topological phase transitions using Calinski-Harabaz index},
  author = {Jielin Wang and Wanzhou Zhang and Tian Hua and Tzu-Chieh Wei},
  journal= {arXiv preprint arXiv:2010.06136},
  year   = {2021}
}

Comments

15 pages, 17 figures