Simplicity of mean-field theories in neural quantum states

TL;DR

This paper demonstrates that neural quantum states can efficiently represent ground states of mean-field models like the TFIM with very few parameters, highlighting their simplicity and potential for scalable quantum simulations.

Contribution

It analytically shows that mean-field ground states require very few neural network parameters, even in the thermodynamic limit, and explores the robustness of this simplicity under symmetry breaking.

Findings

Ground states of mean-field theories require limited neural network parameters.

Convergence to the TFIM ground state can be achieved with a single parameter.

The 1-parameter ansatz remains accurate for a range of long-range interaction exponents.

Abstract

The utilization of artificial neural networks for representing quantum many-body wave functions has garnered significant attention, with enormous recent progress for both ground states and non-equilibrium dynamics. However, quantifying state complexity within this neural quantum states framework remains elusive. In this study, we address this key open question from the complementary point of view: Which states are simple to represent with neural quantum states? Concretely, we show on a general level that ground states of mean-field theories with permutation symmetry only require a limited number of independent neural network parameters. We analytically establish that, in the thermodynamic limit, convergence to the ground state of the fully-connected transverse-field Ising model (TFIM), the mean-field Ising model, can be achieved with just one single parameter. Expanding our analysis, we explore the behavior of the 1-parameter ansatz under breaking of the permutation symmetry. For that purpose, we consider the TFIM with tunable long-range interactions, characterized by an interaction exponent $\alpha$. We show analytically that the 1-parameter ansatz for the neural quantum state still accurately captures the ground state for a whole range of values for $0\le \alpha \le 1$, implying a mean-field description of the model in this regime.