Universality classes and machine learning

Abstract

Abstract We formulate the problem of the universality class investigation using machine learning. We chose an example of the universality class of the two-dimensional 4-state Potts model. There are four known models within the universality class – the 4-state Potts model, the Baxter-Wu model, the Ashkin-Teller model, and the Turban model. All four of them together are not equivalent in the Hamiltonian representation, in the lattice symmetry, and the layout of spins on the lattice. We generate statistically independent datasets for all models using the same Monte Carlo technique. The machine learning methods will be used for the analysis of the universality class of models based on generated datasets.