Constructing exact representations of quantum many-body systems with deep neural networks

Abstract

We develop a constructive approach to generate artificial neural networks representing the exact ground states of a large class of many-body lattice Hamiltonians. It is based on the deep Boltzmann machine architecture, in which two layers of hidden neurons mediate quantum correlations among physical degrees of freedom in the visible layer. The approach reproduces the exact imaginary-time Hamiltonian evolution, and is completely deterministic. In turn, compact and exact network representations for the ground states are obtained without stochastic optimization of the network parameters. The number of neurons grows linearly with the system size and total imaginary time, respectively. Physical quantities can be measured by sampling configurations of both physical and neuron degrees of freedom. We provide specific examples for the transverse-field Ising and Heisenberg models by implementing efficient sampling. As a compact, classical representation for many-body quantum systems, our approach is an alternative to the standard path integral, and it is potentially useful also to systematically improve on numerical approaches based on the restricted Boltzmann machine architecture.

References in corpus (19)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Many-body quantum state tomography with neural networks
• Stochastic series expansion method with operator-loop update
• Cluster Algorithm for Vertex Models
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Machine Learning Topological States
• Equivalence of restricted Boltzmann machines and tensor network states
• Approximating quantum many-body wave-functions using artificial neural networks
• Bold Diagrammatic Monte Carlo: When Sign Problem is Welcome
• Variational Monte Carlo Method Combined with Quantum-Number Projection and Multi-Variable Optimization
• Solving the Bose-Hubbard model with machine learning
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Chiral Topological Phases from Artificial Neural Networks
• Path-Integral Renormalization Group Method for Numerical Study on Ground States of Strongly Correlated Electronic Systems
• Learning hard quantum distributions with variational autoencoders
• Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
• Neural Network Operations and Susuki-Trotter evolution of Neural Network States

Cited by in corpus (104)

• Machine learning and the physical sciences
• Discovering physical concepts with neural networks
• Identifying topological order through unsupervised machine learning
• 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
• Quantum Entanglement in Deep Learning Architectures
• Constructing neural stationary states for open quantum many-body systems
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Experimental neural network enhanced quantum tomography
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Variational Quantum Boltzmann Machines
• Neural tensor contractions and the expressive power of deep neural quantum states
• Machine learning assisted quantum state estimation
• Neural network quantum state tomography in a two-qubit experiment
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Neural network representation of tensor network and chiral states
• Variational Benchmarks for Quantum Many-Body Problems
• Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• Neural-network quantum state tomography
• Matrix Model simulations using Quantum Computing, Deep Learning, and Lattice Monte Carlo
• The learnability scaling of quantum states: restricted Boltzmann machines
• Improving the dynamics of quantum sensors with reinforcement learning
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Autonomous tuning and charge state detection of gate defined quantum dots
• Deep learning of quantum entanglement from incomplete measurements
• Recipes for when Physics Fails: Recovering Robust Learning of Physics Informed Neural Networks
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Deep Learning-Enhanced Variational Monte Carlo Method for Quantum Many-Body Physics
• Generalized Transfer Matrix States from Artificial Neural Networks
• Purifying Deep Boltzmann Machines for Thermal Quantum States
• Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• A Neural-Network Variational Quantum Algorithm for Many-Body Dynamics
• QuCumber: wavefunction reconstruction with neural networks
• Self-learning projective quantum Monte Carlo simulations guided by restricted Boltzmann machines
• Exact representations of many body interactions with RBM neural networks
• Neural-network quantum states at finite temperature
• Gradient-descent quantum process tomography by learning Kraus operators
• Machine Learning Quantum States -- Extensions to Fermion-Boson Coupled Systems and Excited-State Calculations
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• Automatic Differentiable Monte Carlo: Theory and Application
• Laser pulse driven control of charge and spin order in the two-dimensional Kondo lattice
• Dynamical large deviations of two-dimensional kinetically constrained models using a neural-network state ansatz
• Simulating disordered quantum systems via dense and sparse restricted Boltzmann machines
• Restricted Boltzmann Machines and Matrix Product States of 1D Translational Invariant Stabilizer Codes
• Transforming Generalized Ising Model into Boltzmann Machine
• Entanglement Features of Random Neural Network Quantum States
• Gaussian Process States: A data-driven representation of quantum many-body physics
• Variational Quantum-Neural Hybrid Error Mitigation
• Data-Driven Dynamical Mean-Field Theory: an error-correction approach to solve the quantum many-body problem using machine learning
• Boltzmann machines as two-dimensional tensor networks
• Quantum State Tomography with Conditional Generative Adversarial Networks
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Mean-Field Density Matrix Decompositions
• Matrix Product States with Backflow correlations
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• Variational Quantum Algorithms for Steady States of Open Quantum Systems
• Classification and reconstruction of optical quantum states with deep neural networks
• A framework for efficient ab initio electronic structure with Gaussian Process States
• Bayesian Optimization of Bose-Einstein Condensates
• Sampling scheme for neuromorphic simulation of entangled quantum systems
• Compact Neural-network Quantum State representations of Jastrow and Stabilizer states
• Continuous-time dynamics and error scaling of noisy highly-entangling quantum circuits
• Phase diagram reconstruction of the Bose-Hubbard model with a Restricted Boltzmann Machine wavefunction
• Emulating Quantum Interference with Generalized Ising Machines
• 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
• Amplitude Ratios and Neural Network Quantum States
• Simplicity of mean-field theories in neural quantum states
• Network-Initialized Monte Carlo Based on Generative Neural Networks
• A deep neural network approach to solve the Dirac equation
• Deep learning quantum Monte Carlo for solids
• Neural Network Quantum States analysis of the Shastry-Sutherland model
• Geometry and symmetry in quantum Boltzmann machine
• Sampling asymmetric open quantum systems for artificial neural networks
• Predicting quantum many-body dynamics with transferable neural networks
• Hamiltonian Learning using Machine Learning Models Trained with Continuous Measurements
• Boltzmann machines and quantum many-body problems
• Beyond single-reference fixed-node approximation in ab initio Diffusion Monte Carlo using antisymmetrized geminal power applied to systems with hundreds of electrons
• Specialising Neural-network Quantum States for the Bose Hubbard Model
• Neural network representation of quantum systems
• Exact block encoding of imaginary time evolution with universal quantum neural networks
• Multi-body wave function of ground and low-lying excited states using unornamented deep neural networks
• Supervised and unsupervised learning of the many-body critical phase, phase transitions, and critical exponents in disordered quantum systems
• Machine Learning Wavefunction
• Variational Neural and Tensor Network Approximations of Thermal States
• Phase classification in the long-range Harper model using machine learning
• Machine learning, quantum chaos, and pseudorandom evolution
• Improving neural network performance for solving quantum sign structure
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Machine-learning-inspired quantum control in many-body dynamics
• Analogy between Boltzmann machines and Feynman path integrals
• Classifying topological neural network quantum states via diffusion maps
• Emergence of global receptive fields capturing multipartite quantum correlations
• Seeding neural network quantum states with tensor network states
• Accuracy of Restricted Boltzmann Machines for the one-dimensional $J_1-J_2$ Heisenberg model
• Universal Spin Models are Universal Approximators in Machine Learning
• Predicting sampling advantage of stochastic Ising Machines for Quantum Simulations
• Learning agent-based approach to the characterization of open quantum systems
• Efficient bit encoding of neural networks for Fock states
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning
• Fast evaluation of interaction integrals for confined systems with machine learning