Infinite Neural Network Quantum States: Entanglement and Training Dynamics

Abstract

We study infinite limits of neural network quantum states ($\infty$-NNQS), which exhibit representation power through ensemble statistics, and also tractable gradient descent dynamics. Ensemble averages of Renyi entropies are expressed in terms of neural network correlators, and architectures that exhibit volume-law entanglement are presented. A general framework is developed for studying the gradient descent dynamics of neural network quantum states (NNQS), using a quantum state neural tangent kernel (QS-NTK). For $\infty$-NNQS the training dynamics is simplified, since the QS-NTK becomes deterministic and constant. An analytic solution is derived for quantum state supervised learning, which allows an $\infty$-NNQS to recover any target wavefunction. Numerical experiments on finite and infinite NNQS in the transverse field Ising model and Fermi Hubbard model demonstrate excellent agreement with theory. $\infty$-NNQS opens up new opportunities for studying entanglement and training dynamics in other physics applications, such as in finding ground states.

References in corpus (48)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Average Entropy of a Subsystem
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Many-body quantum state tomography with neural networks
• Deep Neural Networks as Gaussian Processes
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• 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
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Emergent statistical mechanics of entanglement in random unitary circuits
• Recurrent Neural Network Wave Functions
• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• The Principles of Deep Learning Theory
• Quantum many-body dynamics in two dimensions with artificial neural networks
• Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
• Variational neural network ansatz for steady states in open quantum systems
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• 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
• Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
• Neural Quantum States of frustrated magnets: generalization and sign structure
• Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
• Asymptotically unbiased estimation of physical observables with neural samplers
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• Deep Convolutional Networks as shallow Gaussian Processes
• Neural tensor contractions and the expressive power of deep neural quantum states
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• Gaussian Process Behaviour in Wide Deep Neural Networks
• Classical variational simulation of the Quantum Approximate Optimization Algorithm
• Neural Networks and Quantum Field Theory
• Neural network representation of tensor network and chiral states
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• Phases of two-dimensional spinless lattice fermions with first-quantized deep neural-network quantum states
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
• Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
• Finite Versus Infinite Neural Networks: an Empirical Study
• Deep Quantum Geometry of Matrices
• Real time evolution with neural-network quantum states
• Calculating Renyi Entropies with Neural Autoregressive Quantum States
• Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics
• A quantum algorithm for training wide and deep classical neural networks
• Entanglement Area Law for Shallow and Deep Quantum Neural Network States
• Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators
• Spacetime Neural Network for High Dimensional Quantum Dynamics
• Entanglement transitions from restricted Boltzmann machines

Cited by in corpus (4)

• Neural-network quantum states for many-body physics
• Learning ground states of gapped quantum Hamiltonians with Kernel Methods
• Bound on entanglement in neural quantum states
• Investigating Stark many-body localization with continuous unitary transformation flows