Neural tensor contractions and the expressive power of deep neural quantum states

Abstract

We establish a direct connection between general tensor networks and deep feed-forward artificial neural networks. The core of our results is the construction of neural-network layers that efficiently perform tensor contractions, and that use commonly adopted non-linear activation functions. The resulting deep networks feature a number of edges that closely matches the contraction complexity of the tensor networks to be approximated. In the context of many-body quantum states, this result establishes that neural-network states have strictly the same or higher expressive power than practically usable variational tensor networks. As an example, we show that all matrix product states can be efficiently written as neural-network states with a number of edges polynomial in the bond dimension and depth logarithmic in the system size. The opposite instead does not hold true, and our results imply that there exist quantum states that are not efficiently expressible in terms of matrix product states or PEPS, but that are instead efficiently expressible with neural network states.

References in corpus (32)

• The density-matrix renormalization group in the age of matrix product states
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• An Area Law for One Dimensional Quantum Systems
• Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
• Many-body quantum state tomography with neural networks
• Tensor networks for complex quantum systems
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Quantum Entanglement in Neural Network States
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• The computational complexity of PEPS
• Machine Learning Topological States
• Recurrent Neural Network Wave Functions
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Fermionic neural-network states for ab-initio electronic structure
• Equivalence of restricted Boltzmann machines and tensor network states
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Quantum many-body dynamics in two dimensions with artificial neural networks
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Quantum Entanglement in Deep Learning Architectures
• Constructing exact representations of quantum many-body systems with deep neural networks
• Chiral Topological Phases from Artificial Neural Networks
• A class of highly entangled many-body states that can be efficiently simulated
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• Scaling of entanglement entropy in the (branching) multi-scale entanglement renormalization ansatz
• Contracting projected entangled pair states is average-case hard
• Generalized Transfer Matrix States from Artificial Neural Networks
• Expressive power of complex-valued restricted Boltzmann machines for solving non-stoquastic Hamiltonians
• Locally accurate MPS approximations for ground states of one-dimensional gapped local Hamiltonians
• Approximating power of machine-learning ansatz for quantum many-body states

Cited by in corpus (49)

• Efficient quantum state tomography with convolutional neural networks
• Optimizing Design Choices for Neural Quantum States
• Neural-network quantum states for many-body physics
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Dynamics with autoregressive neural quantum states: application to critical quench dynamics
• A perspective on machine learning and data science for strongly correlated electron problems
• Transformer Wave Function for two dimensional frustrated magnets: emergence of a Spin-Liquid Phase in the Shastry-Sutherland Model
• Reconstructing complex states of a 20-qubit quantum simulator
• Variational Neural-Network Ansatz for Continuum Quantum Field Theory
• Atomic Quantum Technologies for Quantum Matter and Fundamental Physics Applications
• Neural Projected Quantum Dynamics: a systematic study
• Unifying view of fermionic neural network quantum states: From neural network backflow to hidden fermion determinant states
• Matrix Product States with Backflow correlations
• Experimental sample-efficient quantum state tomography via parallel measurements
• Neural-Shadow Quantum State Tomography
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• Wave function network description and Kolmogorov complexity of quantum many-body systems
• Neural-network quantum states for a two-leg Bose-Hubbard ladder under magnetic flux
• Autoregressive neural quantum states of Fermi Hubbard models
• Ground State Properties of Quantum Skyrmions described by Neural Network Quantum States
• Deep learning lattice gauge theories
• Tensor Network Computations That Capture Strict Variationality, Volume Law Behavior, and the Efficient Representation of Neural Network States
• Variational Tensor Neural Networks for Deep Learning
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Lee-Yang theory of quantum phase transitions with neural network quantum states
• Simplicity of mean-field theories in neural quantum states
• Generating coupled cluster code for modern distributed memory tensor software
• Approximately-symmetric neural networks for quantum spin liquids
• Neural Network Quantum States analysis of the Shastry-Sutherland model
• Non-stabilizerness of Neural Quantum States
• Variational Neural and Tensor Network Approximations of Thermal States
• Neural-network quantum state study of the long-range antiferromagnetic Ising chain
• Classifying topological neural network quantum states via diffusion maps
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Seeding neural network quantum states with tensor network states
• Universal Performance Gap of Neural Quantum States Applied to the Hofstadter-Bose-Hubbard Model
• Bound on entanglement in neural quantum states
• Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations
• Simulating dynamics of the two-dimensional transverse-field Ising model: a comparative study of large-scale classical numerics
• 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
• Artificial intelligence for representing and characterizing quantum systems
• Computable and noncomputable in the quantum domain: statements and conjectures
• Hybrid between biologically and quantum-inspired many-body states
• Group Convolutional Neural Network for the Low-Energy Spectrum in the Quantum Dimer Model
• Basis dependence of Neural Quantum States for the Transverse Field Ising Model
• Quantum Machine Learning for State Tomography Using Classical Data
• Adaptive quantum dynamics with the time-dependent variational Monte Carlo method