Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems

Abstract

We develop deep autoregressive networks with multi channels to compute many-body systems with \emph{continuous} spin degrees of freedom directly. As a concrete example, we embed the two-dimensional XY model into the continuous-mixture networks and rediscover the Kosterlitz-Thouless (KT) phase transition on a periodic square lattice. Vortices characterizing the quasi-long range order are accurately detected by the autoregressive neural networks. By learning the microscopic probability distributions from the macroscopic thermal distribution, the neural networks compute the free energy directly and find that free vortices and anti-vortices emerge in the high-temperature regime. As a more precise evaluation, we compute the helicity modulus to determine the KT transition temperature. Although the training process becomes more time-consuming with larger lattice sizes, the training time remains unchanged around the KT transition temperature. The continuous-mixture autoregressive networks we developed thus can be potentially used to study other many-body systems with continuous degrees of freedom.

rewrite the whole manuscript. 6 pages, 4 figures, comments welcome

References in corpus (13)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
• Variational neural network ansatz for steady states in open quantum systems
• Constructing neural stationary states for open quantum many-body systems
• Machine learning vortices at the Kosterlitz-Thouless transition
• Unsupervised machine learning and band topology
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Large-scale Monte Carlo simulation of two-dimensional classical XY model using multiple GPUs
• Deep Learning Beyond Lefschetz Thimbles
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Deep learning stochastic processes with QCD phase transition
• Detecting Chiral Magnetic Effect via Deep Learning

Cited by in corpus (8)

• Exploring QCD matter in extreme conditions with Machine Learning
• Phase Transition Study meets Machine Learning
• Reconstructing the neutron star equation of state from observational data via automatic differentiation
• Diffusion Models as Stochastic Quantization in Lattice Field Theory
• Fourier-Flow model generating Feynman paths
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Simulating first-order phase transition with hierarchical autoregressive networks
• Building imaginary-time thermal field theory with artificial neural networks