Efficient Representation of Quantum Many-body States with Deep Neural Networks

Abstract

The challenge of quantum many-body problems comes from the difficulty to represent large-scale quantum states, which in general requires an exponentially large number of parameters. Recently, a connection has been made between quantum many-body states and the neural network representation (\textit{arXiv:1606.02318}). An important open question is what characterizes the representational power of deep and shallow neural networks, which is of fundamental interest due to popularity of the deep learning methods. Here, we give a rigorous proof that a deep neural network can efficiently represent most physical states, including those generated by any polynomial size quantum circuits or ground states of many body Hamiltonians with polynomial-size gaps, while a shallow network through a restricted Boltzmann machine cannot efficiently represent those states unless the polynomial hierarchy in computational complexity theory collapses.

12 pages, 7 figures

References in corpus (7)

• The density-matrix renormalization group in the age of matrix product states
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Simulating Hamiltonian dynamics with a truncated Taylor series
• Criticality, the area law, and the computational power of PEPS
• Quantum simulation of time-dependent Hamiltonians and the convenient illusion of Hilbert space
• Strings, Projected Entangled Pair States, and variational Monte Carlo methods
• Quantum Supremacy for Simulating A Translation-Invariant Ising Spin Model

Cited by in corpus (212)

• Machine learning and the physical sciences
• Many-body quantum state tomography with neural networks
• Discovering physical concepts with neural networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Reconstructing quantum states with generative models
• The Expressive Power of Parameterized Quantum Circuits
• 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
• Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• 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
• Constructing neural stationary states for open quantum many-body systems
• Machine-learned multi-system surrogate models for materials prediction
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Machine learning meets quantum physics
• Constructing exact representations of quantum many-body systems with deep neural networks
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Machine Learning for Quantum Matter
• Quantum Adversarial Machine Learning
• Kernel methods for interpretable machine learning of order parameters
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Tree Tensor Networks for Generative Modeling
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Machine learning for long-distance quantum communication
• 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
• Classical Shadows With Noise
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Solving frustrated quantum many-particle models with convolutional neural networks
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Quantum Neural Network States: A Brief Review of Methods and Applications
• Quantum Machine Learning: from physics to software engineering
• Neural tensor contractions and the expressive power of deep neural quantum states
• Deep Learning and AdS/CFT
• Neural Gutzwiller-projected variational wave functions
• Quantum error correction for the toric code using deep reinforcement learning
• 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
• Autoregressive Transformer Neural Network for Simulating Open Quantum Systems via a Probabilistic Formulation
• Machine Learning Spatial Geometry from Entanglement Features
• Learning hard quantum distributions with variational autoencoders
• Self-learning Monte Carlo with Deep Neural Networks
• Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Learning Disordered Topological Phases by Statistical Recovery of Symmetry
• Machine learning non-local correlations
• Neural network representation of tensor network and chiral states
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• 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
• Experimental quantum homodyne tomography via machine learning
• Machine learning the deuteron
• Geometry of learning neural quantum states
• Supervised Learning with Projected Entangled Pair States
• Machine Learning meets Quantum Foundations: A Brief Survey
• AdS/CFT as a deep Boltzmann machine
• Learning phase transitions from dynamics
• Smallest Neural Network to Learn the Ising Criticality
• Matrix Model simulations using Quantum Computing, Deep Learning, and Lattice Monte Carlo
• Quantum dynamics in transverse-field Ising models from classical networks
• The learnability scaling of quantum states: restricted Boltzmann machines
• Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models
• Optimizing Design Choices for Neural Quantum States
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• Improving the dynamics of quantum sensors with reinforcement learning
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Machine learning assisted readout of trapped-ion qubits
• Investigating ultrafast quantum magnetism with machine learning
• Interpreting machine learning of topological quantum phase transitions
• Machine learning \& artificial intelligence in the quantum domain
• Eigenstate extraction with neural-network tomography
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Can Boltzmann Machines Discover Cluster Updates ?
• Method to solve quantum few-body problems with artificial neural networks
• Quantum computing for chemistry and physics applications from a Monte Carlo perspective
• Neural-network quantum states for many-body physics
• Deep Learning-Enhanced Variational Monte Carlo Method for Quantum Many-Body Physics
• Purifying Deep Boltzmann Machines for Thermal Quantum States
• Projective quantum Monte Carlo simulations guided by unrestricted neural network states
• Generalized Transfer Matrix States from Artificial Neural Networks
• Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
• Quantum Codes from Neural Networks
• Reducing Autocorrelation Times in Lattice Simulations with Generative Adversarial Networks
• Deep Reinforcement Learning for Efficient Measurement of Quantum Devices
• Gauge equivariant neural networks for quantum lattice gauge theories
• Solving the Liouvillian Gap with Artificial Neural Networks
• Unsupervised learning using topological data augmentation
• A Neural-Network Variational Quantum Algorithm for Many-Body Dynamics
• Mode-Assisted Unsupervised Learning of Restricted Boltzmann Machines
• QuCumber: wavefunction reconstruction with neural networks
• 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
• Expressive power of complex-valued restricted Boltzmann machines for solving non-stoquastic Hamiltonians
• Deep Quantum Geometry of Matrices
• Compressing deep neural networks by matrix product operators
• Self-learning projective quantum Monte Carlo simulations guided by restricted Boltzmann machines
• Efficient Quantum State Sample Tomography with Basis-dependent Neural-networks
• Neural-network quantum states at finite temperature
• Machine Learning Quantum States -- Extensions to Fermion-Boson Coupled Systems and Excited-State Calculations
• Protocol Discovery for the Quantum Control of Majoranas by Differentiable Programming and Natural Evolution Strategies
• Approximating power of machine-learning ansatz for quantum many-body states
• Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
• Reconstructing complex states of a 20-qubit quantum simulator
• Estimating expectation values using approximate quantum states
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Identifying Product Order with Restricted Boltzmann Machines
• Real time evolution with neural-network quantum states
• Long-Range Entangled-Plaquette States for Critical and Frustrated Quantum Systems on a Lattice
• Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines
• Adaptive Quantum State Tomography with Active Learning
• A duplication-free quantum neural network for universal approximation
• Applications of deep learning to relativistic hydrodynamics
• Active Learning Algorithm for Computational Physics
• Restricted Boltzmann Machines and Matrix Product States of 1D Translational Invariant Stabilizer Codes
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• Neural Network Operations and Susuki-Trotter evolution of Neural Network States
• Entanglement Features of Random Neural Network Quantum States
• Gaussian Process States: A data-driven representation of quantum many-body physics
• Transforming Generalized Ising Model into Boltzmann Machine
• Correlation-pattern-based Continuous-variable Entanglement Detection through Neural Networks
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Generalized overlap quantum state tomography
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• Wave function network description and Kolmogorov complexity of quantum many-body systems
• Multi-faceted machine learning of competing orders in disordered interacting systems
• Three Learning Stages and Accuracy-Efficiency Tradeoff of Restricted Boltzmann Machines
• Neural-network quantum states for a two-leg Bose-Hubbard ladder under magnetic flux
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Bayesian Optimization of Bose-Einstein Condensates
• Deep learning of many-body observables and quantum information scrambling
• Efficient learning of mixed-state tomography for photonic quantum walk
• Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• Thermometry of one-dimensional Bose gases with neural networks
• Machine-learning approach to finite-size effects in systems with strongly interacting fermions
• Deep reinforcement learning for preparation of thermal and prethermal quantum states
• Sampling scheme for neuromorphic simulation of entangled quantum systems
• Compact Neural-network Quantum State representations of Jastrow and Stabilizer states
• Emulating Quantum Interference with Generalized Ising Machines
• Ground State Properties of Quantum Skyrmions described by Neural Network Quantum States
• Deep Neural Networks as Variational Solutions for Correlated Open Quantum Systems
• Autoregressive neural quantum states of Fermi Hubbard models
• Phase diagram reconstruction of the Bose-Hubbard model with a Restricted Boltzmann Machine wavefunction
• Exponentially improved efficient machine learning for quantum many-body states with provable guarantees
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Adversarial Machine Learning Phases of Matter
• Invariant Neural Network Ansatz for weakly symmetric Open Quantum Lattices
• Neural-network Quantum States for Spin-1 systems: spin-basis and parameterization effects on compactness of representations
• Statistical-mechanical study of deep Boltzmann machine given weight parameters after training by singular value decomposition
• Machine-learning-inspired quantum optimal control of nonadiabatic geometric quantum computation via reverse engineering
• The Discrete Langevin Machine: Bridging the Gap Between Thermodynamic and Neuromorphic Systems
• Amplitude Ratios and Neural Network Quantum States
• Stack operation of tensor networks
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Entropy, Free Energy, and Work of Restricted Boltzmann Machines
• Predicting quantum many-body dynamics with transferable neural networks
• Efficiency of neural quantum states in light of the quantum geometric tensor
• Exact block encoding of imaginary time evolution with universal quantum neural networks
• Compressing Neural Networks Using Tensor Networks with Exponentially Fewer Variational Parameters
• Boltzmann machines and quantum many-body problems
• Neural-network Quantum State of Transverse-field Ising Model
• Dual-Capability Machine Learning Models for Quantum Hamiltonian Parameter Estimation and Dynamics Prediction
• Specialising Neural-network Quantum States for the Bose Hubbard Model
• Deep learning of topological phase transitions from entanglement aspects for two-dimensional chiral p-wave superconductors
• The Role of Quantum Computing in Advancing Scientific High-Performance Computing: A perspective from the ADAC Institute
• Machine Learning Wavefunction
• Variational Neural and Tensor Network Approximations of Thermal States
• Entanglement transitions from restricted Boltzmann machines
• Probing transport in quantum many-fermion simulations via quantum loop topography
• Tensor networks and efficient descriptions of classical data
• Exploring explicit coarse-grained structure in artificial neural networks
• State Classification via a Random-Walk-Based Quantum Neural Network
• Time-dependent variational principle for open quantum systems with artificial neural networks
• Machine learning the deuteron: new architectures and uncertainty quantification
• Hidden self-energies as origin of cuprate superconductivity revealed by machine learning
• A differentiable programming framework for spin models
• Preparing Quantum States by Measurement-feedback Control with Bayesian Optimization
• Efficient Characterization of Quantum Evolutions via a Recommender System
• Reinforcement learning to learn quantum states for Heisenberg scaling accuracy
• Unconditionally separating noisy ${\mathsf{QNC}}^0$ from bounded polynomial threshold circuits of constant depth
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Classifying topological neural network quantum states via diffusion maps
• Improving neural network performance for solving quantum sign structure
• Efficiency of neural-network state representations of one-dimensional quantum spin systems
• Generalization Error Estimates of Machine Learning Methods for Solving High Dimensional Schrödinger Eigenvalue Problems
• Emergence of global receptive fields capturing multipartite quantum correlations
• Artificial intelligence for representing and characterizing quantum systems
• Representing arbitrary ground states of toric code by a restricted Boltzmann machine
• Universal Performance Gap of Neural Quantum States Applied to the Hofstadter-Bose-Hubbard Model
• Entanglement Clustering for ground-stateable quantum many-body states
• Seeding neural network quantum states with tensor network states
• Bound on entanglement in neural quantum states
• Variational Transformer Ansatz for the Density Operator of Steady States in Dissipative Quantum Many-Body Systems
• Universal Spin Models are Universal Approximators in Machine Learning
• Brute-force positivization of $J_1-J_2$ model ground states
• The toric code under antiferromagnetic isotropic Heisenberg interactions
• Bootstrapping Flat-band Superconductors: Rigorous Lower Bounds on Superfluid Stiffness
• Group Convolutional Neural Network for the Low-Energy Spectrum in the Quantum Dimer Model
• Tensorization of neural networks for improved privacy and interpretability
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning
• Quantum Machine Learning for State Tomography Using Classical Data