Finite-size analysis in neural network classification of critical phenomena

Abstract

We analyze the problem of supervised learning of ferromagnetic phase transitions from the statistical physics perspective. We consider two systems in two universality classes, the two-dimensional Ising model and two-dimensional Baxter-Wu model, and perform careful finite-size analysis of the results of the supervised learning of the phases of each model. We find that the variance of the neural network (NN) output function (VOF) as a function of temperature has a peak in the critical region. Qualitatively, the VOF is related to the classification rate of the NN. We find that the width of the VOF peak displays the finite-size scaling governed by the correlation length exponent, $\nu$, of the universality class of the model. We check this conclusion using several NN architectures -- a fully connected NN, a convolutional NN and several members of the ResNet family -- and discuss the accuracy of the extracted critical exponents $\nu$.

arXiv comment5 pages, 2 figures + Supplementary materials; published version

References in corpus (9)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Machine learning phases of matter
• Machine learning of phase transitions in the percolation and XY models
• Parameter diagnostics of phases and phase transition learning by neural networks
• Machine-Learning Studies on Spin Models
• Cluster Monte Carlo: Scaling of Systematic Errors in the 2D Ising Model
• Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transitions in the q-state clock models
• Critical amplitude ratios of the Baxter-Wu model
• Can a CNN trained on the Ising model detect the phase transition of the $q$-state Potts model?

Cited by in corpus (9)

• Neural density functional theory of liquid-gas phase coexistence
• Why hyperdensity functionals describe any equilibrium observable
• Unsupervised learning of phase transitions via modified anomaly detection with autoencoders
• Learning the bulk and interfacial physics of liquid-liquid phase separation with neural density functionals
• Machine learning of phases and structures for model systems in physics
• Phase determination with and without deep learning
• Influence of anisotropy on the study of critical behavior of spin models by machine learning methods
• Machine Learning Domain Adaptation in Spin Models with Continuous Phase Transitions
• Phase probabilities in first-order transitions using machine learning