Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition

Abstract

We investigate the connection between the supervised learning of the binary phase classification in the ferromagnetic Ising model and the standard finite-size-scaling theory of the second-order phase transition. Proposing a minimal one-free-parameter neural network model, we analytically formulate the supervised learning problem for the canonical ensemble being used as a training data set. We show that just one free parameter is capable enough to describe the data-driven emergence of the universal finite-size-scaling function in the network output that is observed in a large neural network, theoretically validating its critical point prediction for unseen test data from different underlying lattices yet in the same universality class of the Ising criticality. We also numerically demonstrate the interpretation with the proposed one-parameter model by providing an example of finding a critical point with the learning of the Landau mean-field free energy being applied to the real data set from the uncorrelated random scale-free graph with a large degree exponent.

References in corpus (47)

• An efficient, multiple range random walk algorithm to calculate the density of states
• Machine learning and the physical sciences
• Machine learning phases of matter
• Determining the density of states for classical statistical models: A random walk algorithm to produce a flat histogram
• Explainable Machine Learning for Scientific Insights and Discoveries
• Learning phase transitions by confusion
• Generation of uncorrelated random scale-free networks
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Ising Model on Networks with an Arbitrary Distribution of Connections
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Machine learning vortices at the Kosterlitz-Thouless transition
• Detection of phase transition via convolutional neural network
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Machine Learning for Quantum Matter
• Kernel methods for interpretable machine learning of order parameters
• Finite-size scaling in complex networks
• Critical phenomena in networks
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Machine learning of phase transitions in the percolation and XY models
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Machine learning of quantum phase transitions
• Unveiling phase transitions with machine learning
• Machine Learning for Condensed Matter Physics
• Parameter diagnostics of phases and phase transition learning by neural networks
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Probing hidden spin order with interpretable machine learning
• Machine-Learning Studies on Spin Models
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Super-resolving the Ising model with convolutional neural networks
• Learning multiple order parameters with interpretable machines
• Smallest Neural Network to Learn the Ising Criticality
• Applications of neural networks to the studies of phase transitions of two-dimensional Potts models
• Machine Learning as a universal tool for quantitative investigations of phase transition
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Interpretable Machine Learning Study of Many-Body Localization Transition in Disordered Quantum Ising Spin Chains
• Learning the Ising Model with Generative Neural Networks
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Extracting Critical Exponent by Finite-Size Scaling with Convolutional Neural Networks
• Phase transition encoded in neural network
• Deep neural networks for direct, featureless learning through observation: the case of 2d spin models
• Identification of hidden order and emergent constraints in frustrated magnets using tensorial kernel methods
• Learning to find order in disorder
• Restricted Boltzmann Machine Flows and The Critical Temperature of Ising models