Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
This work addresses the challenge of accurately simulating statistical distributions in lattice models like the Ising model, but it is incremental as it highlights limitations in capturing correlations.
The study applied a variational autoencoder to generate Ising model spin configurations from a low-dimensional latent space, finding that while the generated distributions qualitatively matched training data and indicated phase transitions, spin correlations were suppressed leading to unphysically high energies.
Variational autoencoders employ an encoding neural network to generate a probabilistic representation of a data set within a low-dimensional space of latent variables followed by a decoding stage that maps the latent variables back to the original variable space. Once trained, a statistical ensemble of simulated data realizations can be obtained by randomly assigning values to the latent variables that are subsequently processed by the decoding section of the network. To determine the accuracy of such a procedure when applied to lattice models, an autoencoder is here trained on a thermal equilibrium distribution of Ising spin realizations. When the output of the decoder for synthetic data is interpreted probabilistically, spin realizations can be generated by randomly assigning spin values according to the computed likelihood. The resulting state distribution in energy-magnetization space then qualitatively resembles that of the training samples. However, because correlations between spins are suppressed, the computed energies are unphysically large for low-dimensional latent variable spaces. The features of the learned distributions as a function of temperature, however, provide a qualitative indication of the presence of a phase transition and the distribution of realizations with characteristic cluster sizes.