Super-resolving the Ising model with convolutional neural networks

Abstract

Machine learning is becoming widely used in condensed matter physics. Inspired by the concept of image super-resolution, we propose a method to increase the size of lattice spin configurations using deep convolutional neural networks. Through supervised learning on Monte Carlo (MC) generated spin configurations, we train networks that invert real-space renormalization decimations. We demonstrate that super-resolution can reproduce thermodynamic observables that agree with MC calculations for the one and two-dimensional Ising model at various temperatures. We find that it is possible to predict thermodynamic quantities for lattice sizes larger than those used in training by extrapolating the parameters of the network. We use this method to extrapolate the exponents of the 2D Ising critical point towards the thermodynamic limit, which results in good agreement with theory.

References in corpus (16)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Many-body quantum state tomography with neural networks
• Discovering Phase Transitions with Unsupervised Learning
• Computational Studies of Quantum Spin Systems
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Learning Thermodynamics with Boltzmann Machines
• Machine Learning Phases of Strongly Correlated Fermions
• Mutual Information, Neural Networks and the Renormalization Group
• Machine learning vortices at the Kosterlitz-Thouless transition
• Neural Network Renormalization Group
• Latent Space Purification via Neural Density Operators
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Machine learning action parameters in lattice quantum chromodynamics
• Projective quantum Monte Carlo simulations guided by unrestricted neural network states

Cited by in corpus (41)

• Machine Learning for Condensed Matter Physics
• Efficient Modelling of Trivializing Maps for Lattice ${\varphi }^4$ Theory Using Normalizing Flows: A First Look at Scalability
• Machine Learning Holographic Mapping by Neural Network Renormalization Group
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Riemannian geometry and automatic differentiation for optimization problems of quantum physics and quantum technologies
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Learning the Ising Model with Generative Neural Networks
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Generative models for sampling and phase transition indication in spin systems
• Scalable neural networks for the efficient learning of disordered quantum systems
• Inverse Renormalization Group in Quantum Field Theory
• Inverse Renormalization Group based on Image Super-Resolution using Deep Convolutional Networks
• Neural Monte Carlo Renormalization Group
• A Deep Learning Functional Estimator of Optimal Dynamics for Sampling Large Deviations
• Machine-Learning Study using Improved Correlation Configuration and Application to Quantum Monte Carlo Simulation
• Convolutional restricted Boltzmann machine aided Monte Carlo: An application to Ising and Kitaev models
• Machine learning of XY model on a spherical Fibonacci lattice
• Neural networks in quantum many-body physics: a hands-on tutorial
• Machine learning for structure-property relationships: Scalability and limitations
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Phase determination with and without deep learning
• Machine learning of phases and structures for model systems in physics
• Conservation Laws and Spin System Modeling through Principal Component Analysis
• Network-Initialized Monte Carlo Based on Generative Neural Networks
• A learning algorithm with emergent scaling behavior for classifying phase transitions
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• 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
• Liouville Space Neural Network Representation of Density Matrices
• Quaternion-based machine learning on topological quantum systems
• The Autodidactic Universe
• Machine Learning Domain Adaptation in Spin Models with Continuous Phase Transitions
• A differentiable programming framework for spin models
• Inverse renormalization group of spin glasses
• A Group-Equivariant Autoencoder for Identifying Spontaneously Broken Symmetries
• Scanning-probe and information-concealing machine learning intermediate hexatic phase and critical scaling of solid-hexatic phase transition in deformable particles
• Revisiting the dynamics of Bose-Einstein condensates in a double well by deep learning with a hybrid network
• Dreaming up scale invariance via inverse renormalization group
• Feature extraction of machine learning and phase transition point of Ising model
• Learning disentangled representation for classical models
• Faithfulness of Real-Space Renormalization Group Maps