Einstein-Podolsky-Rosen steering based on semi-supervised machine learning

TL;DR

This paper introduces a semi-supervised machine learning approach to detect EPR steering in quantum states, reducing the need for extensive labeled data and improving detection accuracy.

Contribution

It proposes a semi-supervised support vector machine method for quantum steering detection, which requires fewer labeled states than traditional supervised methods.

Findings

Significant accuracy improvements demonstrated

Requires fewer labeled quantum states

Effective in detecting EPR steering

Abstract

Einstein-Podolsky-Rosen(EPR)steering is a kind of powerful nonlocal quantum resource in quantum information processing such as quantum cryptography and quantum communication. Many criteria have been proposed in the past few years to detect the steerability both analytically and numerically. Supervised machine learning such as support vector machines and neural networks have also been trained to detect the EPR steerability. To implement supervised machine learning, one needs a lot of labeled quantum states by using the semidefinite programming, which is very time consuming. We present a semi-supervised support vector machine method which only uses a small portion of labeled quantum states in detecting quantum steering. We show that our approach can significantly improve the accuracies by detailed examples.