Network-Initialized Monte Carlo Based on Generative Neural Networks

Abstract

We design generative neural networks that generate Monte Carlo configurations with complete absence of autocorrelation from which only short Markov chains are needed before making measurements for physical observables, irrespective of the system locating at the classical critical point, fermionic Mott insulator, Dirac semimetal, or quantum critical point. We further propose a network-initialized Monte Carlo scheme based on such neural networks, which provides independent samplings and can accelerate the Monte Carlo simulations by significantly reducing the thermalization process. We demonstrate the performance of our approach on the two-dimensional Ising and fermion Hubbard models, and expect it can systematically speed up the Monte Carlo simulations especially for the very challenging many-electron problems.

References in corpus (51)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Stochastic series expansion method with operator-loop update
• Quantum spin-liquid emerging in two-dimensional correlated Dirac fermions
• Computational Studies of Quantum Spin Systems
• Exact, Complete, and Universal Continuous-Time Worldline Monte Carlo Approach to the Statistics of Discrete Quantum Systems
• Machine learning quantum phases of matter beyond the fermion sign problem
• Absence of a Spin Liquid Phase in the Hubbard Model on the Honeycomb Lattice
• Pinning the order: the nature of quantum criticality in the Hubbard model on honeycomb lattice
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Unsupervised Generative Modeling Using Matrix Product States
• Machine Learning Phases of Strongly Correlated Fermions
• Self-Learning Monte Carlo Method
• Symmetries and many-body excited states with neural-network quantum states
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Approximating quantum many-body wave-functions using artificial neural networks
• Constructing exact representations of quantum many-body systems with deep neural networks
• Neural Network Renormalization Group
• Machine Learning for Quantum Matter
• Tree Tensor Networks for Generative Modeling
• Correlation-induced insulating topological phases at charge neutrality in twisted bilayer graphene
• Is magic-angle twisted bilayer graphene near a quantum critical point?
• Machine Learning for Condensed Matter Physics
• Self-Learning Monte Carlo Method in Fermion Systems
• Charge-Density-Wave Transitions of Dirac Fermions Coupled to Phonons
• Self-Learning Determinantal Quantum Monte Carlo Method
• Quantum Monte Carlo simulation of the chiral Heisenberg Gross-Neveu-Yukawa phase transition with a single Dirac cone
• Non-Fermi-liquid at (2+1)d ferromagnetic quantum critical point
• Momentum space quantum Monte Carlo on twisted bilayer Graphene
• Super-resolving the Ising model with convolutional neural networks
• Self-Learning Monte Carlo Method: Continuous-Time Algorithm
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Symmetry Enforced Self-Learning Monte Carlo Method Applied to the Holstein Model
• Matrix Product Operators for Sequence to Sequence Learning
• Itinerant Quantum Critical Point with Fermion Pockets and Hot Spots
• Itinerant quantum critical point with frustration and non-Fermi-liquid
• Revealing Fermionic Quantum Criticality from New Monte Carlo Techniques
• Designer Monte Carlo Simulation for Gross-Neveu Transition
• Unbiased Monte Carlo Cluster Updates with Autoregressive Neural Networks
• Dynamical properties of collective excitations in twisted bilayer Graphene
• Correlated Insulating Phases in the Twisted Bilayer Graphene
• Recommender Engine for Continuous Time Quantum Monte Carlo Methods
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Generative models for sampling and phase transition indication in spin systems
• EMUS-QMC: Elective Momentum Ultra-Size Quantum Monte Carlo Method
• The dynamical exponent of a quantum critical itinerant ferromagnet: a Monte Carlo study
• Convolutional restricted Boltzmann machine aided Monte Carlo: An application to Ising and Kitaev models
• Quantum self-learning Monte Carlo with quantum Fourier transform sampler

Cited by in corpus (1)

• Self-supervised graph neural networks for accurate prediction of Néel temperature