Learning the Ising Model with Generative Neural Networks

Abstract

Recent advances in deep learning and neural networks have led to an increased interest in the application of generative models in statistical and condensed matter physics. In particular, restricted Boltzmann machines (RBMs) and variational autoencoders (VAEs) as specific classes of neural networks have been successfully applied in the context of physical feature extraction and representation learning. Despite these successes, however, there is only limited understanding of their representational properties and limitations. To better understand the representational characteristics of RBMs and VAEs, we study their ability to capture physical features of the Ising model at different temperatures. This approach allows us to quantitatively assess learned representations by comparing sample features with corresponding theoretical predictions. Our results suggest that the considered RBMs and convolutional VAEs are able to capture the temperature dependence of magnetization, energy, and spin-spin correlations. The samples generated by RBMs are more evenly distributed across temperature than those generated by VAEs. We also find that convolutional layers in VAEs are important to model spin correlations whereas RBMs achieve similar or even better performances without convolutional filters.

arXiv comment18 pages, 13 figures

References in corpus (15)

• Variational Inference: A Review for Statisticians
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A high-bias, low-variance introduction to Machine Learning for physicists
• Many-body quantum state tomography with neural networks
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Inverse statistical problems: from the inverse Ising problem to data science
• Learning Thermodynamics with Boltzmann Machines
• Mutual Information, Neural Networks and the Renormalization Group
• Cluster Variation Method in Statistical Physics and Probabilistic Graphical Models
• Neural Network Renormalization Group
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Toward an AI Physicist for Unsupervised Learning
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Super-resolving the Ising model with convolutional neural networks
• Smallest Neural Network to Learn the Ising Criticality

Cited by in corpus (21)

• Social physics
• Mott transition in a cavity-boson system: A quantitative comparison between theory and experiment
• Transfer learning of phase transitions in percolation and directed percolation
• Machine learning generated configurations in presence of a conserved quantity: a cautionary tale
• Can a CNN trained on the Ising model detect the phase transition of the $q$-state Potts model?
• Machine Learning Etudes in Conformal Field Theories
• Machine Learning of Nonequilibrium Phase Transition in an Ising Model on Square Lattice
• Machine learning for structure-property relationships: Scalability and limitations
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Generative Neural Samplers for the Quantum Heisenberg Chain
• Phase determination with and without deep learning
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Machine learning of phases and structures for model systems in physics
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Thermodynamics of the Ising model encoded in restricted Boltzmann machines
• Energy Transfer in Random-Matrix ensembles of Floquet Hamiltonians
• Supervised Training of Neural-Network Quantum States for the Next Nearest Neighbor Ising model
• Minimalist Neural Networks training for phase classification in diluted-Ising models
• Machine Learning Percolation Model
• Entanglement in the Quantum Spherical Model -- a Review
• Learning disentangled representation for classical models