Deep Learning on the 2-Dimensional Ising Model to Extract the Crossover Region with a Variational Autoencoder

Abstract

The 2-dimensional Ising model on a square lattice is investigated with a variational autoencoder in the non-vanishing field case for the purpose of extracting the crossover region between the ferromagnetic and paramagnetic phases. The encoded latent variable space is found to provide suitable metrics for tracking the order and disorder in the Ising configurations that extends to the extraction of a crossover region in a way that is consistent with expectations. The extracted results achieve an exceptional prediction for the critical point as well as agreement with previously published results on the configurational magnetizations of the model. The performance of this method provides encouragement for the use of machine learning to extract meaningful structural information from complex physical systems where little a priori data is available.

References in corpus (21)

• The NumPy array: a structure for efficient numerical computation
• Exchange Monte Carlo Method and Application to Spin Glass Simulations
• Simulated Tempering: A New Monte Carlo Scheme
• Machine learning phases of matter
• Hidden Order in the Cuprates
• Quantum phase transitions
• Discovering Phase Transitions with Unsupervised Learning
• Quantum criticality
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Singular Fermi Liquids
• Learning Thermodynamics with Boltzmann Machines
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Hidden Orbital Order in $UR{u}_{2}S{i}_2$
• Helicity Order: Hidden Order Parameter in URu${}_2$Si${}_2$
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Universality in the three-dimensional random-field Ising model
• Cooperative Model of Bacterial Sensing
• Smallest Neural Network to Learn the Ising Criticality
• Universality from disorder in the random-bond Blume-Capel model
• Identifying structural changes with unsupervised machine learning methods

Cited by in corpus (17)

• Exploring QCD matter in extreme conditions with Machine Learning
• Can a CNN trained on the Ising model detect the phase transition of the $q$-state Potts model?
• Machine Learning of Nonequilibrium Phase Transition in an Ising Model on Square Lattice
• Mean-field Coherent Ising Machines with artificial Zeeman terms
• Machine Learning the Square-Lattice Ising Model
• Generative Neural Samplers for the Quantum Heisenberg Chain
• Machine learning of phases and structures for model systems in physics
• Phase determination with and without deep learning
• Deep learning of phase transitions with minimal examples
• Minimalist Neural Networks training for phase classification in diluted-Ising models
• Application of the Variational Autoencoder to Detect the Critical Points of the Anisotropic Ising Model
• Predicting the Mpemba Effect Using Machine Learning
• Self-Supervised Ensemble Learning: A Universal Method for Phase Transition Classification of Many-Body Systems
• A Group-Equivariant Autoencoder for Identifying Spontaneously Broken Symmetries
• Energy based diffusion generator for efficient sampling of Boltzmann distributions
• Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders
• A Unsupervised Framework for Identifying Diverse Quantum Phase Transitions Using Classical Shadow Tomography