Neural Monte Carlo Renormalization Group

Abstract

The key idea behind the renormalization group (RG) transformation is that properties of physical systems with very different microscopic makeups can be characterized by a few universal parameters. However, finding the optimal RG transformation remains difficult due to the many possible choices of the weight factors in the RG procedure. Here we show, by identifying the conditional distribution in the restricted Boltzmann machine (RBM) and the weight factor distribution in the RG procedure, an optimal real-space RG transformation can be learned without prior knowledge of the physical system. This neural Monte Carlo RG algorithm allows for direct computation of the RG flow and critical exponents. This scheme naturally generates a transformation that maximizes the real-space mutual information between the coarse-grained region and the environment. Our results establish a solid connection between the RG transformation in physics and the deep architecture in machine learning, paving the way to further interdisciplinary research.

arXiv comment11 pages, 7 figures

References in corpus (16)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Learning phase transitions by confusion
• Why does deep and cheap learning work so well?
• A Finite Size Scaling Study of Lattice Models in the three-dimensional Ising Universality Class
• Mutual Information, Neural Networks and the Renormalization Group
• Machine Learning for Quantum Matter
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Super-resolving the Ising model with convolutional neural networks
• Monte Carlo Renormalization of the 3-D Ising model: Analyticity and Convergence
• Thermodynamics and Feature Extraction by Machine Learning
• Optimal Renormalization Group Transformation from Information Theory
• The surprising convergence of the Monte Carlo renormalization group for the d=3 Ising Model
• A Variational Approach to Monte Carlo Renormalization Group
• Determination of the Critical Manifold Tangent Space and Curvature with Monte Carlo Renormalization Group

Cited by in corpus (8)

• Signal detection in nearly continuous spectra and symmetry breaking
• Categorical Representation Learning and RG flow operators for algorithmic classifiers
• Corrections to scaling in the 3D Ising model: a comparison between MC and MCRG results
• Monte Carlo renormalization group calculation for the d=3 Ising Model using a modified transformation
• Relevant Analytic Spontaneous Magnetization Relation for the Face-Centered-Cubic Ising Lattice
• Dreaming up scale invariance via inverse renormalization group
• Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
• Faithfulness of Real-Space Renormalization Group Maps