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 (13)

• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• The Principles of Deep Learning Theory
• 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
• Constructing neural stationary states for open quantum many-body systems
• Neural tensor contractions and the expressive power of deep neural quantum states
• Finite Versus Infinite Neural Networks: an Empirical Study
• Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics
• A quantum algorithm for training wide and deep classical neural networks
• 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