Entanglement Area Law for Shallow and Deep Quantum Neural Network States

Abstract

A study of the artificial neural network representation of quantum many-body states is presented. The locality and entanglement properties of states for shallow and deep quantum neural networks are investigated in detail. By introducing the notion of local quasi-product states, for which the locally connected shallow feed-forward neural network states and restricted Boltzmann machine states are special cases, we show that Rényi entanglement entropies of all these states obey the entanglement area law. Besides, we also investigate the entanglement features of deep Boltzmann machine states and show that locality constraints imposed on the neural networks make the states obey the entanglement area law. Finally, as an application, we apply the notion of Rényi entanglement entropy to understanding the power of neural networks and show that image classification problems which can be efficiently solved must obey the area law.

References in corpus (49)

• Topological Insulators
• Topological insulators and superconductors
• Fault-tolerant quantum computation by anyons
• Non-Abelian Anyons and Topological Quantum Computation
• Anyons in an exactly solved model and beyond
• Holographic Derivation of Entanglement Entropy from AdS/CFT
• The World as a Hologram
• Area laws for the entanglement entropy - a review
• Topological entanglement entropy
• Efficient classical simulation of slightly entangled quantum computations
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Persistent entanglement in arrays of interacting particles
• The holographic principle
• Measurement-based quantum computation with cluster states
• Average Entropy of a Subsystem
• Machine learning phases of matter
• Entanglement renormalization
• Topological orders and Edge excitations in FQH states
• Many-body quantum state tomography with neural networks
• Holographic quantum error-correcting codes: Toy models for the bulk/boundary correspondence
• Bulk Locality and Quantum Error Correction in AdS/CFT
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• Quantum Entanglement in Neural Network States
• Cluster-state quantum computation
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Machine Learning Topological States
• Quantum Loop Topography for Machine Learning
• Holographic quantum matter
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Average Entropy of a Subsystem
• Matrix Product States for dynamical simulation of infinite chains
• A Neural Decoder for Topological Codes
• Maximally multipartite entangled states
• An exact mapping between the Variational Renormalization Group and Deep Learning
• Quantum Neural Network States: A Brief Review of Methods and Applications
• Stochastic Error Cancellation in Analog Quantum Simulation
• Boundary-bulk relation in topological orders
• Topological order in 1D Cluster state protected by symmetry
• Machine Learning Spatial Geometry from Entanglement Features
• Neural network representation of tensor network and chiral states
• Using Recurrent Neural Networks to Optimize Dynamical Decoupling for Quantum Memory
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• AdS/CFT as a deep Boltzmann machine
• Holography as deep learning
• Efficient Machine Learning Representations of Surface Code with Boundaries, Defects, Domain Walls and Twists
• Bulk-Boundary Correspondence in the Quantum Hall Effect
• An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
• Entanglement Entropy of Target Functions for Image Classification and Convolutional Neural Network

Cited by in corpus (8)

• Tensor networks for interpretable and efficient quantum-inspired machine learning
• Boundary and domain wall theories of 2d generalized quantum double model
• Deep learning of many-body observables and quantum information scrambling
• Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Entanglement transitions from restricted Boltzmann machines
• Classifying topological neural network quantum states via diffusion maps
• Variational Transformer Ansatz for the Density Operator of Steady States in Dissipative Quantum Many-Body Systems