Neural network representation of tensor network and chiral states

Abstract

We study the representational power of Boltzmann machines (a type of neural network) in quantum many-body systems. We prove that any (local) tensor network state has a (local) neural network representation. The construction is almost optimal in the sense that the number of parameters in the neural network representation is almost linear in the number of nonzero parameters in the tensor network representation. Despite the difficulty of representing (gapped) chiral topological states with local tensor networks, we construct a quasi-local neural network representation for a chiral $p$-wave superconductor. These results demonstrate the power of Boltzmann machines.

v2: introduction expanded; close to the published version

References in corpus (17)

• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Matrix product states represent ground states faithfully
• Quantum Entanglement in Neural Network States
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Equivalence of restricted Boltzmann machines and tensor network states
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Constructing exact representations of quantum many-body systems with deep neural networks
• Approximating Gibbs states of local Hamiltonians efficiently with PEPS
• Stochastic Error Cancellation in Analog Quantum Simulation
• Chiral Topological Phases from Artificial Neural Networks
• Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• Grassmann tensor network states and its renormalization for strongly correlated fermionic and bosonic states
• Local tensor network for strongly correlated projective states
• Area law in one dimension: Degenerate ground states and Renyi entanglement entropy
• Boltzmann machines as two-dimensional tensor networks

Cited by in corpus (46)

• Machine learning and the physical sciences
• Discovering physical concepts with neural networks
• Fermionic neural-network states for ab-initio electronic structure
• Lecture Notes of Tensor Network Contractions
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Efficient quantum state tomography with convolutional neural networks
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Machine Learning meets Quantum Foundations: A Brief Survey
• Self-Learning Monte Carlo Method: Continuous-Time Algorithm
• Holography as deep learning
• Neural-network quantum states for many-body physics
• Efficient Machine Learning Representations of Surface Code with Boundaries, Defects, Domain Walls and Twists
• Self-learning Monte Carlo method with Behler-Parrinello neural networks
• Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• Artificial Neural Network in Cosmic Landscape
• jVMC: Versatile and performant variational Monte Carlo leveraging automated differentiation and GPU acceleration
• Quantum State Tomography with Locally Purified Density Operators and Local Measurements
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization
• Spin-1/2 kagome Heisenberg antiferromagnet: Machine learning discovery of the spinon pair density wave ground state
• Neural-Shadow Quantum State Tomography
• 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
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Investigating Network Parameters in Neural-Network Quantum States
• Boltzmann machines and quantum many-body problems
• Entanglement transitions from restricted Boltzmann machines
• Machine Learning Wavefunction
• Variational Neural and Tensor Network Approximations of Thermal States
• Time-dependent variational principle for open quantum systems with artificial neural networks
• Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks
• Scale-Invariant Continuous Entanglement Renormalization of a Chern Insulator
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Representation Theorem for Matrix Product States
• Efficiency of neural-network state representations of one-dimensional quantum spin systems
• Countering adversarial perturbations in graphs using error correcting codes
• Representing arbitrary ground states of toric code by a restricted Boltzmann machine
• Seeding neural network quantum states with tensor network states
• Repesentation of general spin-$S$ systems using a Restricted Boltzmann Machine with Softmax Regression
• Learning a compass spin model with neural network quantum states
• Group Convolutional Neural Network for the Low-Energy Spectrum in the Quantum Dimer Model
• The toric code under antiferromagnetic isotropic Heisenberg interactions
• Quantum Machine Learning for State Tomography Using Classical Data