Quantum Entanglement in Neural Network States

Abstract

Machine learning, one of today's most rapidly growing interdisciplinary fields, promises an unprecedented perspective for solving intricate quantum many-body problems. Understanding the physical aspects of the representative artificial neural-network states is recently becoming highly desirable in the applications of machine learning techniques to quantum many-body physics. Here, we study the quantum entanglement properties of neural-network states, with a focus on the restricted-Boltzmann-machine (RBM) architecture. We prove that the entanglement of all short-range RBM states satisfies an area law for arbitrary dimensions and bipartition geometry. For long-range RBM states we show by using an exact construction that such states could exhibit volume-law entanglement, implying a notable capability of RBM in representing efficiently quantum states with massive entanglement. We further examine generic RBM states with random weight parameters. We find that their averaged entanglement entropy obeys volume-law scaling and meantime strongly deviates from the Page-entropy of the completely random pure states. We show that their entanglement spectrum has no universal part associated with random matrix theory and bears a Poisson-type level statistics. Using reinforcement learning, we demonstrate that RBM is capable of finding the ground state (with power-law entanglement) of a model Hamiltonian with long-range interaction. In addition, we show, through a concrete example of the one-dimensional symmetry-protected topological cluster states, that the RBM representation may also be used as a tool to analytically compute the entanglement spectrum. Our results uncover the unparalleled power of artificial neural networks in representing quantum many-body states, which paves a novel way to bridge computer science based machine learning techniques to outstanding quantum condensed matter physics problems.

17 pages, 8 figures. Version published in Phys. Rev. X

References in corpus (92)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• Quantum Machine Learning
• The density-matrix renormalization group in the age of matrix product states
• The density-matrix renormalization group
• Entanglement Entropy and Quantum Field Theory
• Area laws for the entanglement entropy - a review
• Topological entanglement entropy
• Many body localization and thermalization in quantum statistical mechanics
• Efficient classical simulation of slightly entangled quantum computations
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Detecting topological order in a ground state wave function
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Scaling of Entanglement close to a Quantum Phase Transitions
• Entropy and Area
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Geometric and Renormalized Entropy in Conformal Field Theory
• Entanglement Spectrum as a Generalization of Entanglement Entropy: Identification of Topological Order in Non-Abelian Fractional Quantum Hall Effect States
• Measurement-based quantum computation with cluster states
• Average Entropy of a Subsystem
• The many-body localization phase transition
• Entanglement in a simple quantum phase transition
• Machine learning phases of matter
• Symmetry protected topological orders and the group cohomology of their symmetry group
• Information in Black Hole Radiation
• Measuring entanglement entropy through the interference of quantum many-body twins
• Quantum thermalization through entanglement in an isolated many-body system
• An Area Law for One Dimensional Quantum Systems
• Multi-party entanglement in graph states
• The distribution of the ratio of consecutive level spacings in random matrix ensembles
• Tensor-Entanglement-Filtering Renormalization Approach and Symmetry Protected Topological Order
• Classical simulation of infinite-size quantum lattice systems in one spatial dimension
• A class of quantum many-body states that can be efficiently simulated
• On Geometric Entropy
• Entanglement Renormalization and Holography
• Unifying time evolution and optimization with matrix product states
• Learning phase transitions by confusion
• Matrix product states represent ground states faithfully
• Classical simulation of infinite-size quantum lattice systems in two spatial dimensions
• Discovering Phase Transitions with Unsupervised Learning
• Many-body localization in a disordered quantum Ising chain
• Area laws in a many-body localized state and its implications for topological order
• Quantum Spin Chain, Toeplitz Determinants and Fisher-Hartwig Conjecture
• Jerusalem Lectures on Black Holes and Quantum Information
• Entropy scaling and simulability by Matrix Product States
• Entanglement and quantum phase transition in the extended Hubbard model
• Local entanglement and quantum phase transition in the Hubbard model
• General Relationship Between the Entanglement Spectrum and the Edge State Spectrum of Topological Quantum States
• Measuring entanglement growth in quench dynamics of bosons in an optical lattice
• Entanglement spectrum in one-dimensional systems
• Cluster-state quantum computation
• Entanglement spectrum of topological insulators and superconductors
• Machine learning quantum phases of matter beyond the fermion sign problem
• Measuring multipartite entanglement via dynamic susceptibilities
• Bipartite entanglement and entropic boundary law in lattice spin systems
• Entanglement spectrum and boundary theories with projected entangled-pair states
• Entanglement in XY Spin Chain
• Ground state entanglement and geometric entropy in the Kitaev's model
• Learning Thermodynamics with Boltzmann Machines
• Does a single eigenstate encode the full Hamiltonian?
• Self-Learning Monte Carlo Method
• Measuring entanglement entropy of a generic many-body system with a quantum switch
• 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
• DeSitter entropy, quantum entanglement and ADS/CFT
• A Neural Decoder for Topological Codes
• Bulk-Edge Correspondence in the Entanglement Spectra
• Hamiltonian complexity
• Obtaining highly-excited eigenstates of many-body localized Hamiltonians by the density matrix renormalization group
• An exact mapping between the Variational Renormalization Group and Deep Learning
• Quantum Hamiltonian Complexity
• Many body localization and thermalization: insights from the entanglement spectrum
• An area law for entanglement from exponential decay of correlations
• Entanglement in Quantum Spin Chains, Symmetry Classes of Random Matrices, and Conformal Field Theory
• Many-body localisation implies that eigenvectors are matrix-product states
• Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data
• Measurement Protocol for the Entanglement Spectrum of Cold Atoms
• Multipartite entanglement detection in bosons
• Single-copy entanglement in critical spin chains
• Supervised Learning with Quantum-Inspired Tensor Networks
• Stochastic Error Cancellation in Analog Quantum Simulation
• Emergent irreversibility and entanglement spectrum statistics
• Two-component Structure in the Entanglement Spectrum of Highly Excited States
• Topological order in 1D Cluster state protected by symmetry
• Entanglement Across a Transition to Quantum Chaos
• Deep learning and the renormalization group
• Restricted Boltzmann Machines for the Long Range Ising Models
• Machine learning for many-body physics: efficient solution of dynamical mean-field theory
• Statistical Bubble Localization with Random Interactions
• Area law in one dimension: Degenerate ground states and Renyi entanglement entropy
• Entanglement Measures for Quasi-Two-Dimensional Fractional Quantum Hall States
• Detecting intermediate mass black holes in globular clusters with machine learning
• Measuring quantum entanglement, machine learning and wave function tomography: Bridging theory and experiment with the quantum gas microscope

Cited by in corpus (260)

• Machine learning and the physical sciences
• Circuit-centric quantum classifiers
• Discovering physical concepts with neural networks
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Reconstructing quantum states with generative models
• The Expressive Power of Parameterized Quantum Circuits
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Symmetries and many-body excited states with neural-network quantum states
• Equivalence of restricted Boltzmann machines and tensor network states
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Provably efficient machine learning for quantum many-body problems
• Simulation methods for open quantum many-body systems
• Exploring entanglement and optimization within the Hamiltonian Variational Ansatz
• Approximating quantum many-body wave-functions using artificial neural networks
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Quantum Entanglement in Deep Learning Architectures
• Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment
• Constructing neural stationary states for open quantum many-body systems
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Genuine quantum correlations in quantum many-body systems: a review of recent progress
• Machine learning meets quantum physics
• NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Machine Learning for Quantum Matter
• Probing many-body localization with neural networks
• Quantum Adversarial Machine Learning
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Machine learning out-of-equilibrium phases of matter
• Latent Space Purification via Neural Density Operators
• Kernel methods for interpretable machine learning of order parameters
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Dirac-type nodal spin liquid revealed by refined quantum many-body solver using neural-network wave function, correlation ratio, and level spectroscopy
• Solving the Bose-Hubbard model with machine learning
• Tree Tensor Networks for Generative Modeling
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Machine learning of phase transitions in the percolation and XY models
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Solving frustrated quantum many-particle models with convolutional neural networks
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Neural tensor contractions and the expressive power of deep neural quantum states
• Deep Learning and AdS/CFT
• Neural Gutzwiller-projected variational wave functions
• Chiral Topological Phases from Artificial Neural Networks
• Quenches near Ising quantum criticality as a challenge for artificial neural networks
• Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal
• Neural network quantum state tomography in a two-qubit experiment
• Deep Learning Topological Invariants of Band Insulators
• Machine Learning Spatial Geometry from Entanglement Features
• Self-learning Monte Carlo with Deep Neural Networks
• Automatic spin-chain learning to explore the quantum speed limit
• Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Neural network representation of tensor network and chiral states
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Entanglement Classification via Neural Network Quantum States
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
• Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape
• Real space mapping of topological invariants using artificial neural networks
• Methods for simulating string-net states and anyons on a digital quantum computer
• Supervised Learning with Projected Entangled Pair States
• Transformer Quantum State: A Multi-Purpose Model for Quantum Many-Body Problems
• Self-Learning Monte Carlo Method: Continuous-Time Algorithm
• Learning entropy production via neural networks
• Learning phase transitions from dynamics
• Smallest Neural Network to Learn the Ising Criticality
• Unsupervised machine learning of quantum phase transitions using diffusion maps
• Transfer learning for scalability of neural-network quantum states
• Quantum dynamics in transverse-field Ising models from classical networks
• Optimizing Design Choices for Neural Quantum States
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• Principal Component Analysis for Fermionic Critical Points
• Matrix Product Operators for Sequence to Sequence Learning
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas
• Unsupervised learning universal critical behavior via the intrinsic dimension
• Holography as deep learning
• Experimental Simultaneous Learning of Multiple Non-Classical Correlations
• Investigating ultrafast quantum magnetism with machine learning
• Interpreting machine learning of topological quantum phase transitions
• Deep learning of quantum entanglement from incomplete measurements
• Machine learning \& artificial intelligence in the quantum domain
• Imaginary components of out-of-time correlators and information scrambling for navigating the learning landscape of a quantum machine learning model
• Eigenstate extraction with neural-network tomography
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Neural-network states for the classical simulation of quantum computing
• Dynamical Phase Transitions in models of Collective Neutrino Oscillations
• Can Boltzmann Machines Discover Cluster Updates ?
• Method to solve quantum few-body problems with artificial neural networks
• Neural-network quantum states for many-body physics
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Machine learning dynamical phase transitions in complex networks
• Projective quantum Monte Carlo simulations guided by unrestricted neural network states
• Generalized Transfer Matrix States from Artificial Neural Networks
• Purifying Deep Boltzmann Machines for Thermal Quantum States
• Steerability detection of arbitrary 2-qubit state via machine learning
• U(1) symmetric recurrent neural networks for quantum state reconstruction
• Quantum Codes from Neural Networks
• Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
• Solving the Liouvillian Gap with Artificial Neural Networks
• Role of stochastic noise and generalization error in the time propagation of neural-network quantum states
• Scaling of neural-network quantum states for time evolution
• Unsupervised learning using topological data augmentation
• Combined unitary and symmetric group approach applied to low-dimensional spin systems
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics
• Quantum neural networks to simulate many-body quantum systems
• Efficient Machine Learning Representations of Surface Code with Boundaries, Defects, Domain Walls and Twists
• Extracting Critical Exponent by Finite-Size Scaling with Convolutional Neural Networks
• Efficient Quantum State Sample Tomography with Basis-dependent Neural-networks
• Deep Quantum Geometry of Matrices
• Self-learning Monte Carlo method with Behler-Parrinello neural networks
• Self-learning projective quantum Monte Carlo simulations guided by restricted Boltzmann machines
• Supervised learning of time-independent Hamiltonians for gate design
• Phase Detection with Neural Networks: Interpreting the Black Box
• Neural-network quantum states at finite temperature
• Machine Learning Quantum States -- Extensions to Fermion-Boson Coupled Systems and Excited-State Calculations
• Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
• Reconstructing complex states of a 20-qubit quantum simulator
• Approximating power of machine-learning ansatz for quantum many-body states
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Unitary long-time evolution with quantum renormalization groups and artificial neural networks
• Machine learning electron correlation in a disordered medium
• Identifying Product Order with Restricted Boltzmann Machines
• Dynamical large deviations of two-dimensional kinetically constrained models using a neural-network state ansatz
• Real time evolution with neural-network quantum states
• Tensor networks for interpretable and efficient quantum-inspired machine learning
• Calculating Renyi Entropies with Neural Autoregressive Quantum States
• Machine prediction of topological transitions in photonic crystals
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• A tree tensor network approach to simulating Shor's algorithm
• Mixed State Entanglement Classification using Artificial Neural Networks
• Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets
• Lee-Yang theory of the two-dimensional quantum Ising model
• Restricted Boltzmann Machines and Matrix Product States of 1D Translational Invariant Stabilizer Codes
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• Wishart and random density matrices: Analytical results for the mean-square Hilbert-Schmidt distance
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• Einstein-Podolsky-Rosen steering based on semi-supervised machine learning
• Entanglement Features of Random Neural Network Quantum States
• Entanglement Verification with Deep Semi-supervised Machine Learning
• Can neural quantum states learn volume-law ground states?
• Transforming Generalized Ising Model into Boltzmann Machine
• Boltzmann machines as two-dimensional tensor networks
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Learning epidemic threshold in complex networks by Convolutional Neural Network
• Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Ground state search by local and sequential updates of neural network quantum states
• Quantum Gradient Algorithm for General Polynomials
• Extracting many-particle entanglement entropy from observables using supervised machine learning
• Classifying surface probe images in strongly correlated electronic systems via machine learning
• Neural Projected Quantum Dynamics: a systematic study
• Matrix Product States with Backflow correlations
• Multi-faceted machine learning of competing orders in disordered interacting systems
• Experimental sample-efficient quantum state tomography via parallel measurements
• Entanglement in multinucleon transfer reactions
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• Neural-Shadow Quantum State Tomography
• Wave function network description and Kolmogorov complexity of quantum many-body systems
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Neural-network quantum states for a two-leg Bose-Hubbard ladder under magnetic flux
• Machine learning of XY model on a spherical Fibonacci lattice
• Deep learning of many-body observables and quantum information scrambling
• Autoregressive neural Slater-Jastrow ansatz for variational Monte Carlo simulation
• On the descriptive power of Neural-Networks as constrained Tensor Networks with exponentially large bond dimension
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• Pruning a restricted Boltzmann machine for quantum state reconstruction
• Sampling scheme for neuromorphic simulation of entangled quantum systems
• Magnetic Phases of Spatially-Modulated Spin-1 Chains in Rydberg Excitons: Classical and Quantum Simulations
• Compact Neural-network Quantum State representations of Jastrow and Stabilizer states
• Efficient neural-network based variational Monte Carlo scheme for direct optimization of excited energy states in frustrated quantum systems
• Autoregressive neural quantum states of Fermi Hubbard models
• Deep learning lattice gauge theories
• Impact of conditional modelling for a universal autoregressive quantum state
• An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
• Neural-network Quantum States for Spin-1 systems: spin-basis and parameterization effects on compactness of representations
• Tensor Network Computations That Capture Strict Variationality, Volume Law Behavior, and the Efficient Representation of Neural Network States
• Stabilizer ground states for simulating quantum many-body physics: theory, algorithms, and applications
• Adversarial Machine Learning Phases of Matter
• Distributed quantum machine learning via classical communication
• Machine learning phases of active matter
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Superconducting Optoelectronic Neurons I: General Principles
• Stack operation of tensor networks
• Transformer Wave Function for Quantum Long-Range models
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Investigating Network Parameters in Neural-Network Quantum States
• Sampling asymmetric open quantum systems for artificial neural networks
• Predicting quantum many-body dynamics with transferable neural networks
• Classical Quantum Optimization with Neural Network Quantum States
• Tensor network to learn the wavefunction of data
• Simplicity of mean-field theories in neural quantum states
• Two-dimensional local Hamiltonian problem with area laws is QMA-complete
• Migrating Knowledge between Physical Scenarios based on Artificial Neural Networks
• Non-stabilizerness of Neural Quantum States
• Ground-state properties via machine learning quantum constraints
• Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations
• Liouville Space Neural Network Representation of Density Matrices
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Boltzmann machines and quantum many-body problems
• Experimentally detecting a quantum change point via Bayesian inference
• Deep learning of topological phase transitions from entanglement aspects for two-dimensional chiral p-wave superconductors
• Quantum neural networks with multi-qubit potentials
• Entanglement transitions from restricted Boltzmann machines
• Finding Quantum Critical Points with Neural-Network Quantum States
• Entanglement entropy of XX spin $1/2$ chain with random partitioning at arbitrary temperature
• Machine Learning Wavefunction
• Coarse-grained spectral projection (CGSP): a deep learning-assisted approach to quantum unitary dynamics
• Probing transport in quantum many-fermion simulations via quantum loop topography
• Tensor-network-based variational Monte Carlo approach to the non-equilibrium steady state of open quantum systems
• Variational Neural and Tensor Network Approximations of Thermal States
• Entanglement balance of quantum $(e,2e)$ scattering processes
• Achieving the volume-law entropy regime with random-sign Dicke states
• Time-dependent variational principle for open quantum systems with artificial neural networks
• Learning of error statistics for the detection of quantum phases
• Machine learning, quantum chaos, and pseudorandom evolution
• Neural-network quantum state study of the long-range antiferromagnetic Ising chain
• Neural Quantum State Study of Fracton Models
• Bidirectional information flow quantum state tomography
• Improving neural network performance for solving quantum sign structure
• Deep Learning Super-Diffusion in Multiplex Networks
• Effective temperature in approximate quantum many-body states
• Experimental demonstration of reconstructing quantum states with generative models
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Analogy between Boltzmann machines and Feynman path integrals
• Classifying topological neural network quantum states via diffusion maps
• Efficiency of neural-network state representations of one-dimensional quantum spin systems
• Representing arbitrary ground states of toric code by a restricted Boltzmann machine
• Emergence of global receptive fields capturing multipartite quantum correlations
• An Empirical Study of Quantum Dynamics as a Ground State Problem with Neural Quantum States
• Investigating Stark many-body localization with continuous unitary transformation flows
• Variational Transformer Ansatz for the Density Operator of Steady States in Dissipative Quantum Many-Body Systems
• Learning topological defects formation with neural networks in a quantum phase transition
• Seeding neural network quantum states with tensor network states
• Bound on entanglement in neural quantum states
• Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations
• Entanglement Clustering for ground-stateable quantum many-body states
• Self-regularizing restricted Boltzmann machines
• Kinetic samplers for neural quantum states
• Universal Performance Gap of Neural Quantum States Applied to the Hofstadter-Bose-Hubbard Model
• Efficient bit encoding of neural networks for Fock states
• Basis dependence of Neural Quantum States for the Transverse Field Ising Model
• Neural quantum states for entanglement depth certification from randomized Pauli measurements
• The toric code under antiferromagnetic isotropic Heisenberg interactions
• Machine Learning out of equilibrium correlations in the Bose-Hubbard model
• Neural-Network Quantum States for Periodic Systems in Continuous Space
• Machine learning of the Ising model on a spherical Fibonacci lattice
• Neural Tangent Kernel of Matrix Product States: Convergence and Applications
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning
• Predicting sampling advantage of stochastic Ising Machines for Quantum Simulations
• Group Convolutional Neural Network for the Low-Energy Spectrum in the Quantum Dimer Model
• Learning a compass spin model with neural network quantum states
• Adaptive quantum dynamics with the time-dependent variational Monte Carlo method
• Magnetic correlations in the $SU(3)$ triangular-lattice $t$-$J$ model at finite doping
• Computable and noncomputable in the quantum domain: statements and conjectures