Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions

Abstract

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.

References in corpus (15)

• Learning phase transitions by confusion
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Machine learning vortices at the Kosterlitz-Thouless transition
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Machine learning for many-body physics: The case of the Anderson impurity model
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• An introduction to Monte Carlo methods
• TensorNetwork: A Library for Physics and Machine Learning
• Machine learning dynamical phase transitions in complex networks
• Few-shot machine learning in the three-dimensional Ising model
• Simulating the Ising Model with a Deep Convolutional Generative Adversarial Network
• Exponential Capacity in an Autoencoder Neural Network with a Hidden Layer
• A Cluster Controller for Transition Matrix Calculations
• Accuracy and Efficiency of Simplified Tensor Network Codes

Cited by in corpus (2)

• A perspective on machine learning and data science for strongly correlated electron problems
• A Group-Equivariant Autoencoder for Identifying Spontaneously Broken Symmetries