Machine learning phases of an Abelian gauge theory

TL;DR

This paper demonstrates that a simple supervised neural network can accurately identify phase transitions and physics in a 2D U(1) quantum link model without prior knowledge of the model.

Contribution

It introduces a minimal neural network approach that requires no information about the studied model for phase detection.

Findings

Neural network accurately estimates the critical point.

The network uncovers the correct physics of the phase transition.

A simple NN architecture suffices for phase identification.

Abstract

The phase transition of the two-dimensional $U(1)$ quantum link model on the triangular lattice is investigated by employing a supervised neural network (NN) consisting of only one input layer, one hidden layer of two neurons, and one output layer. No information on the studied model is used when the NN training is conducted. Instead, two artificially made configurations are considered as the training set. Interestingly, the obtained NN not only estimates the critical point accurately but also uncovers the physics correctly. The results presented here imply that a supervised NN, which has a very simple architecture and is trained without any input from the investigated model, can identify the targeted phase structure with high precision.