General Classification of Entanglement Using Machine Learning

TL;DR

This paper introduces a machine learning-based method for classifying multipartite entanglement in qubit systems, achieving high accuracy especially for pure states, and providing a new automated approach to entanglement classification.

Contribution

It presents a novel machine learning framework for classifying entanglement types in multipartite qubit states without explicit entanglement quantification.

Findings

Near-perfect accuracy for pure states

Reduced accuracy for mixed states

Effective classification across different qubit numbers

Abstract

A classification of multipartite entanglement in qubit systems is introduced for pure and mixed states. The classification is based on the robustness of the said entanglement against partial trace operation. Then we use current machine learning and deep learning techniques to automatically classify a random state of two, three and four qubits without the need to compute the amount of the different types of entanglement in each run; rather this is done only in the learning process. The technique shows high, near perfect, accuracy in the case of pure states. As expected, this accuracy drops, more or less, when dealing with mixed states and when increasing the number of parties involved.