Quantum phase detection generalisation from marginal quantum neural network models

TL;DR

This paper demonstrates that quantum convolutional neural networks can generalize phase detection in quantum systems, accurately mapping the entire phase diagram from limited training on integrable points, overcoming label access limitations.

Contribution

It introduces a method to generalize quantum phase detection using neural networks trained on marginal points, enabling phase diagram reconstruction without full labeling.

Findings

Successfully mapped the ANNNI model's phase diagram.

Neural networks trained on integrable points generalized well.

Achieved phase detection without extensive labeled data.

Abstract

Quantum machine learning offers a promising advantage in extracting information about quantum states, e.g. phase diagram. However, access to training labels is a major bottleneck for any supervised approach, preventing getting insights about new physics. In this Letter, using quantum convolutional neural networks, we overcome this limit by determining the phase diagram of a model where analytical solutions are lacking, by training only on marginal points of the phase diagram, where integrable models are represented. More specifically, we consider the axial next-nearest-neighbor Ising (ANNNI) Hamiltonian, which possesses a ferromagnetic, paramagnetic and antiphase, showing that the whole phase diagram can be reproduced.