Bound on entanglement in neural quantum states

Abstract

Variational wavefunctions offer a practical route around the exponential complexity of many-body Hilbert spaces, but their expressive power is often sharply constrained. Matrix product states, for instance, are efficient but limited to area law entangled states. Neural quantum states (NQS) are widely believed to overcome such limitations, yet little is known about their fundamental constraints. Here we prove that feed-forward neural quantum states acting on $n$ spins with $k$ scalar nonlinearities, under certain analyticity assumptions, obey a bound on entanglement entropy for any subregion: $S\le ck\log n$, for a constant $c$. This establishes an NQS analog of the area law constraint for matrix product states and rules out volume law entanglement for NQS with $O(1)$ nonlinearities. We demonstrate analytically and numerically that the scaling with $n$ is tight for a wide variety of NQS. Our work establishes a fundamental constraint on NQS that applies broadly across different network designs, while reinforcing their substantial expressive power.

6+17 pages

References in corpus (33)

• The density-matrix renormalization group in the age of matrix product states
• 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
• Entanglement renormalization
• An Area Law for One Dimensional Quantum Systems
• Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
• 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
• Characterizing the entanglement of symmetric many-particle spin-1/2 systems
• Quantum Entanglement in Deep Learning Architectures
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Neural Quantum States of frustrated magnets: generalization and sign structure
• 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
• Transformer variational wave functions for frustrated quantum spin systems
• Neural network wave functions and the sign problem
• Discovering Quantum Phase Transitions with Fermionic Neural Networks
• Empowering deep neural quantum states through efficient optimization
• A simple linear algebra identity to optimize Large-Scale Neural Network Quantum States
• Accurate Computation of Quantum Excited States with Neural Networks
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Expressive power of complex-valued restricted Boltzmann machines for solving non-stoquastic Hamiltonians
• Can neural quantum states learn volume-law ground states?
• Entanglement Features of Random Neural Network Quantum States
• Solving and visualizing fractional quantum Hall wavefunctions with neural network
• Is attention all you need to solve the correlated electron problem?
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• Learning ground states of gapped quantum Hamiltonians with Kernel Methods
• Infinite Neural Network Quantum States: Entanglement and Training Dynamics
• Approximately-symmetric neural networks for quantum spin liquids

Cited by in corpus (1)

• Basis dependence of Neural Quantum States for the Transverse Field Ising Model