Machine learning technique to find quantum many-body ground states of bosons on a lattice

Abstract

We develop a variational method to obtain many-body ground states of the Bose-Hubbard model using feedforward artificial neural networks. A fully-connected network with a single hidden layer works better than a fully-connected network with multiple hidden layers, and a multi-layer convolutional network is more efficient than a fully-connected network. AdaGrad and Adam are optimization methods that work well. Moreover, we show that many-body ground states with different numbers of atoms can be generated by a single network.

8 pages, 10 figures

References in corpus (8)

• Learning phase transitions by confusion
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
• Solving the Bose-Hubbard model with machine learning
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Quantum phase recognition via unsupervised machine learning

Cited by in corpus (26)

• Constructing neural stationary states for open quantum many-body systems
• A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithms
• Neural-network quantum states for many-body physics
• Superfluidity in the 1D Bose-Hubbard Model
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• Entanglement Features of Random Neural Network Quantum States
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Ground state search by local and sequential updates of neural network quantum states
• Neural-network quantum states for a two-leg Bose-Hubbard ladder under magnetic flux
• Scalable variational Monte Carlo with graph neural ansatz
• Compact Neural-network Quantum State representations of Jastrow and Stabilizer states
• Ground State Properties of Quantum Skyrmions described by Neural Network Quantum States
• Deep Neural Networks as Variational Solutions for Correlated Open Quantum Systems
• Neural-network Quantum States for Spin-1 systems: spin-basis and parameterization effects on compactness of representations
• Lee-Yang theory of quantum phase transitions with neural network quantum states
• Investigating Network Parameters in Neural-Network Quantum States
• Specialising Neural-network Quantum States for the Bose Hubbard Model
• Quantum many-body solver using artificial neural networks and its applications to strongly correlated electron systems
• Boltzmann machines and quantum many-body problems
• Synergy between deep neural networks and the variational Monte Carlo method for small ${}^{4}H{e}_N$ clusters
• Investigation of bi-particle states in gate-array-controlled quantum-dot systems aided by machine learning techniques
• Improving neural network performance for solving quantum sign structure
• Weakly-supervised learning on Schrodinger equation
• Hyperbolic recurrent neural network as the first type of non-Euclidean neural quantum state ansatz
• Machine Learning out of equilibrium correlations in the Bose-Hubbard model