Entanglement Features of Random Neural Network Quantum States

Abstract

Restricted Boltzmann machines (RBMs) are a class of neural networks that have been successfully employed as a variational ansatz for quantum many-body wave functions. Here, we develop an analytic method to study quantum many-body spin states encoded by random RBMs with independent and identically distributed complex Gaussian weights. By mapping the computation of ensemble-averaged quantities to statistical mechanics models, we are able to investigate the parameter space of the RBM ensemble in the thermodynamic limit. We discover qualitatively distinct wave functions by varying RBM parameters, which correspond to distinct phases in the equivalent statistical mechanics model. Notably, there is a regime in which the typical RBM states have near-maximal entanglement entropy in the thermodynamic limit, similar to that of Haar-random states. However, these states generically exhibit nonergodic behavior in the Ising basis, and do not form quantum state designs, making them distinguishable from Haar-random states.

arXiv comment22 pages, 13 figures, close to published version

References in corpus (41)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Anderson Transitions
• Localization of interacting fermions at high temperature
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Entanglement Spectrum as a Generalization of Entanglement Entropy: Identification of Topological Order in Non-Abelian Fractional Quantum Hall Effect States
• Average Entropy of a Subsystem
• Thermodynamic limit of the density matrix renormalization for the spin-1 Heisenberg chain
• An Area Law for One Dimensional Quantum Systems
• The distribution of the ratio of consecutive level spacings in random matrix ensembles
• Measurement-Induced Phase Transitions in the Dynamics of Entanglement
• Measurement-driven entanglement transition in hybrid quantum circuits
• Theory of the phase transition in random unitary circuits with measurements
• Measurement-induced criticality in random quantum circuits
• Holographic duality from random tensor networks
• A class of ansatz wave functions for 1D spin systems and their relation to DMRG
• Measuring Renyi Entanglement Entropy with Quantum Monte Carlo
• Quantum Entanglement in Neural Network States
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• 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
• Quantum many-body dynamics in two dimensions with artificial neural networks
• Neural Network with Unbounded Activation Functions is Universal Approximator
• Quantum Entanglement in Deep Learning Architectures
• Constructing exact representations of quantum many-body systems with deep neural networks
• Machine Learning for Quantum Matter
• Many body localization and thermalization: insights from the entanglement spectrum
• An area law for the entropy of low-energy states
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Machine learning quantum states in the NISQ era
• Entanglement Negativity at Measurement-Induced Criticality
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• Phase transitions in Restricted Boltzmann Machines with generic priors
• Multifractality meets entanglement: relation for non-ergodic extended states
• Entanglement of random vectors
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Neural-network quantum states at finite temperature
• Universal entanglement of typical states in constrained systems
• Entanglement transitions from restricted Boltzmann machines

Cited by in corpus (12)

• Optimizing Design Choices for Neural Quantum States
• Can neural quantum states learn volume-law ground states?
• Renormalization group for measurement and entanglement phase transitions
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• Impact of conditional modelling for a universal autoregressive quantum state
• Variational Neural and Tensor Network Approximations of Thermal States
• Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
• Improving neural network performance for solving quantum sign structure
• Investigating Stark many-body localization with continuous unitary transformation flows
• Bound on entanglement in neural quantum states
• An Empirical Study of Quantum Dynamics as a Ground State Problem with Neural Quantum States
• Threshold (Q, P) Quantum Distillation