Application of the variational autoencoder to detect the critical points of the anisotropic Ising model

(Received 2021; August 2022; accepted 2023; published April 2023) We generalize the previous study on the application of variational autoencoders to the two-dimensional Ising model to a system with anisotropy. Due to the self-duality property of the system, the critical points can be located exactly for the entire range of anisotropic coupling. This presents an excellent test bed for the validity of using a variational autoencoder to characterize an anisotropic classical model. We reproduce the phase diagram for a wide range of anisotropic couplings and temperatures via a variational autoencoder without the explicit construction of an order parameter. Considering that the partition function of (d + 1 )-dimensional anisotropic models can be mapped to that of the d-dimensional quantum spin models, the present study provides numerical evidence that a variational autoencoder can be applied to analyze quantum systems via the quantum Monte Carlo method.

Automated summary

We generalize the application of variational autoencoders to the anisotropic two-dimensional Ising model and provide numerical evidence that a variational autoencoder can be applied to analyze quantum systems. We reproduce the phase diagram without the explicit construction of an order parameter and demonstrate the validity of using a variational autoencoder to characterize anisotropic classical and quantum models.