Artificial neural network states for non-additive systems

TL;DR

This paper introduces neural coherent states, a new neural network-based method for studying non-additive quantum systems, demonstrating significant improvements in modeling the ground state of the Fröhlich impurity model, especially in challenging regimes.

Contribution

The paper proposes neural coherent states, a novel neural network approach for non-additive quantum systems, showing improved accuracy over traditional methods in a case study.

Findings

Neural coherent states effectively learn the ground state of non-additive systems.

Significant improvement over standard coherent states in intermediate coupling regimes.

Method is generic and applicable to various quantum many-particle systems.

Abstract

Methods inspired from machine learning have recently attracted great interest in the computational study of quantum many-particle systems. So far, however, it has proven challenging to deal with microscopic models in which the total number of particles is not conserved. To address this issue, we propose a new variant of neural network states, which we term neural coherent states. Taking the Fr\"ohlich impurity model as a case study, we show that neural coherent states can learn the ground state of non-additive systems very well. In particular, we observe substantial improvement over the standard coherent state estimates in the most challenging intermediate coupling regime. Our approach is generic and does not assume specific details of the system, suggesting wide applications.