Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory

Abstract

We introduce RGFlow, a deep neural network-based real-space renormalization group (RG) framework tailored for continuum scalar field theories. Leveraging generative capabilities of flow-based neural networks, RGFlow autonomously learns real-space RG transformations from data without prior knowledge of the underlying model. In contrast to conventional approaches, RGFlow is bijective (information-preserving) and is optimized based on the principle of minimal mutual information. We demonstrate the method on two examples. The first one is a one-dimensional Gaussian model, where RGFlow is shown to learn the classical decimation rule. The second is the two-dimensional phi^4 theory, where the network successfully identifies a Wilson-Fisher-like critical point and provides an estimate of the correlation-length critical exponent.

arXiv comment13 pages, 5 figures

References in corpus (28)

• Normalizing Flows: An Introduction and Review of Current Methods
• Physics-informed neural networks for inverse problems in nano-optics and metamaterials
• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Mutual Information, Neural Networks and the Renormalization Group
• Hamiltonian Truncation Study of the Phi^4 Theory in Two Dimensions
• Neural Network Renormalization Group
• Deep Learning Enabled Strain Mapping of Single-Atom Defects in 2D Transition Metal Dichalcogenides with Sub-picometer Precision
• Matrix product states and variational methods applied to critical quantum field theory
• Designing Silicon Photonic Devices using Artificial Neural Networks
• An improved lattice measurement of the critical coupling in phi^4_2 theory
• Monte Carlo Simulation Calculation of Critical Coupling Constant for Continuum ϕ^4_2
• $\lambda {\varphi }^4$ Theory I: The Symmetric Phase Beyond NNNNNNNNLO
• Machine Learning Holographic Mapping by Neural Network Renormalization Group
• Holographic duality between $(2+1)$-d quantum anomalous Hall state and $(3+1)$-d topological insulators
• Hybrid Machine Learning for Scanning Near-field Optical Spectroscopy
• Scanning Probe State Recognition With Multi-Class Neural Network Ensembles
• Exact holographic mapping in free fermion systems
• Density matrix renormalization group in a two-dimensional $\lambda {\varphi }^4$ Hamiltonian lattice model
• Finite-size and finite bond dimension effects of tensor network renormalization
• Computing the renormalization group flow of two-dimensional ${\varphi }^4$ theory with tensor networks
• Deep Learning the Functional Renormalization Group
• Optimal Renormalization Group Transformation from Information Theory
• Neural Network flows of low q-state Potts and clock Models
• Neural Monte Carlo Renormalization Group
• Investigations in 1+1 dimensional lattice ${\varphi }^4$ theory
• Deep-Learning-Aided Extraction of Optical Constants in Scanning Near-Field Optical Microscopy
• Monte Carlo renormalization group calculation for the d=3 Ising Model using a modified transformation