Self-learning Monte Carlo method with Behler-Parrinello neural networks

Abstract

We propose a general way to construct an effective Hamiltonian in the Self-learning Monte Carlo method (SLMC), which speeds up Monte Carlo simulations by training an effective model to propose uncorrelated configurations in the Markov chain. Its applications are, however, limited. This is because it is not obvious to find the explicit form of the effective Hamiltonians. Particularly, it is difficult to make trainable effective Hamiltonians including many-body interactions. In order to overcome this critical difficulty, we introduce the Behler-Parrinello neural networks (BPNNs) as "effective Hamiltonian'' without any prior knowledge, which is used to construct the potential-energy surfaces in interacting many particle systems for molecular dynamics. We combine SLMC with BPNN by focusing on a divisibility of Hamiltonian and propose how to construct the element-wise configurations. We apply it to quantum impurity models. We observed significant improvement of the acceptance ratio from 0.01 (the effective Hamiltonian with the explicit form) to 0.76 (BPNN). This drastic improvement implies that the BPNN effective Hamiltonian includes many body interaction, which is omitted in the effective Hamiltonian with the explicit forms. The BPNNs make SLMC more promising.

arXiv comment14 pages, 5 figures

References in corpus (36)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Continuous-time Monte Carlo methods for quantum impurity models
• Machine learning phases of matter
• A continuous-time solver for quantum impurity models
• Learning phase transitions by confusion
• Continuous Time Quantum Monte Carlo method for fermions
• Quantum Entanglement in Neural Network States
• Cluster Algorithm for Vertex Models
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Quantum Loop Topography for Machine Learning
• The Loop Algorithm
• Continuous-time auxiliary field Monte Carlo for quantum impurity models
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Equivalence of restricted Boltzmann machines and tensor network states
• Approximating quantum many-body wave-functions using artificial neural networks
• Detection of phase transition via convolutional neural network
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Diagrammatic Determinantal methods: projective schemes and applications to the Hubbard-Holstein model
• Self-Learning Monte Carlo Method in Fermion Systems
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Self-learning Monte Carlo with Deep Neural Networks
• Self-Learning Determinantal Quantum Monte Carlo Method
• Revisiting the Hybrid Quantum Monte Carlo Method for Hubbard and Electron-Phonon Models
• Neural network representation of tensor network and chiral states
• A weak coupling CTQMC study of the single impurity and periodic Anderson models with s-wave superconducting baths
• Self-Learning Monte Carlo Method: Continuous-Time Algorithm
• Symmetry Enforced Self-Learning Monte Carlo Method Applied to the Holstein Model
• Itinerant quantum critical point with frustration and non-Fermi-liquid
• Construction of Hamiltonians by supervised learning of energy and entanglement spectra
• Recommender Engine for Continuous Time Quantum Monte Carlo Methods
• Phase Diagrams of Three-Dimensional Anderson and Quantum Percolation Models using Deep Three-Dimensional Convolutional Neural Network
• Towards reduction of autocorrelation in HMC by machine learning
• Construction of accurate machine learning force fields for copper and silicon dioxide

Cited by in corpus (16)

• Machine Learning for Condensed Matter Physics
• Exploring QCD matter in extreme conditions with Machine Learning
• Machine Learning Holographic Mapping by Neural Network Renormalization Group
• Self-learning Hybrid Monte Carlo: A First-principles Approach
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Extending machine learning classification capabilities with histogram reweighting
• Advances in machine-learning-based sampling motivated by lattice quantum chromodynamics
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Barriers and Dynamical Paths in Alternating Gibbs Sampling of Restricted Boltzmann Machines
• A learning by confusion approach to characterize phase transitions
• Facilitating {\it ab initio} configurational sampling of multicomponent solids using an on-lattice neural network model and active learning
• Effective Ruderman-Kittel-Kasuya-Yosida-like interaction in diluted double-exchange model: self-learning Monte Carlo approach
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Self-learning Monte Carlo with equivariant Transformer
• A Group-Equivariant Autoencoder for Identifying Spontaneously Broken Symmetries
• Fast-update in self-learning algorithm for continuous-time quantum Monte Carlo