Neural Network Solver for Small Quantum Clusters

TL;DR

This paper introduces a neural network-based solver for small quantum clusters, demonstrating it can accurately compute spectral functions and potentially serve as an impurity solver in many-body physics methods.

Contribution

The paper presents a novel neural network approach for solving the many-body quantum problem in small clusters, achieving high accuracy compared to exact methods.

Findings

Neural network solver accurately reproduces spectral functions.

The approach is comparable to exact diagonalization results.

Potential application as an impurity solver in dynamical mean field theory.

Abstract

Machine learning approaches have recently been applied to the study of various problems in physics. Most of the studies are focused on interpreting the data generated by conventional numerical methods or an existing database. An interesting question is whether it is possible to use a machine learning approach, in particular a neural network, for solving the many-body problem. In this paper, we present a solver for interacting quantum problem for small clusters based on the neural network. We study the small quantum cluster which mimics the single impurity Anderson model. We demonstrate that the neural network based solver provides quantitatively accurate results for the spectral function as compared to the exact diagonalization method. This opens the possibility of utilizing the neural network approach as an impurity solver for other many body numerical approaches, such as dynamical mean field theory.