Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:1709.03617

Learning to Detect Entanglement

Bingjie Wang

Published Sep 11, 2017• 1 citation
arXivHTMLPDF

Abstract

Classifying states as entangled or separable is a fundamental, but expensive task. This paper presents a method, the forest algorithm, to improve the amount of resources needed to detect entanglement. Starting from 'optimized' methods for using geometric criterion to detect entanglement, specific steps are replaced with machine learning models. Tests using numerical simulations indicate that the model is able to declare a state as entangled in fewer steps compared to existing methods. This improvement is achieved without affecting the correctness of the original algorithm.

DOI
10.48550/arxiv.1709.03617

Related papers

Towards efficient and generic entanglement detection by machine learning

Jue Xu, Qi Zhao

Detection of entanglement is an indispensable step to practical quantum computation and communication. Compared with the conventional entanglement witness method based on fidelity, we propose a flexible, machine learning assisted entanglement detection protocol that is robust to different types of noises and sample efficient. In this protocol, an entanglement classifier for a generic entangled state is obtained by training a classical machine learning model with a synthetic dataset. The dataset contains classical features of two types of states and their labels (either entangled or separable). The classical features of a state, which are expectation values of a set of k-local Pauli observables, are estimated sample-efficiently by the classical shadow method. In the numerical simulation, our classifier can detect the entanglement of 4-qubit GHZ states with coherent noise and W states mixed with large white noise, with high accuracy.

arXiv:2211.05592•Nov 10, 2022•0 citations

Separability-entanglement classifier via machine learning

Sirui Lu, Shilin Huang, Keren Li +7 more

The problem of determining whether a given quantum state is entangled lies at the heart of quantum information processing. Despite the many methods---such as the positive partial transpose criterion and the $k$-symmetric extendibility criterion---to tackle this problem, none of them enables a general, practical solution due to the problem's NP-hard complexity. Explicitly, separable states form a high-dimensional convex set of vastly complicated structures. In this work, we build a different separability-entanglement classifier underpinned by machine learning techniques. We use standard tools from machine learning to learn the entanglement feature of arbitrary given quantum states. We perform substantial numerical tests on two-qubit and two-qutrit systems, and the results indicate that our method can outperform the existing methods in generic cases in terms of both speed and accuracy. This opens up avenues to explore quantum entanglement via the machine learning approach.

arXiv:1705.01523•Physical Review A•Jul 13, 2018•117 citations

Entanglement Detection with Fewer Measurements based on the Geometric Criterion

Bingjie Wang, STEPHEN D. BRIERLEY

We present a new technique to reduce the expected number of measurements to declare an unknown quantum state as entangled. Our method is based on the geometric criterion and so requires only local Pauli measurements. Using concentration of measure, we provide a heuristic which allows us to reinterpret a previous decision tree algorithm due to Laskowski et al and that forms the basis for our new algorithm. Numerical simulations show that for three to six qubits we use fewer measurements than either the trivial algorithm or the decision tree algorithm. In addition, our method is easy to construct, assumes no prior knowledge of the system and works for any number of qubits.

arXiv:1602.02099•Feb 5, 2016•0 citations

Machine Learning Based Detection of Quantum Entanglement in Two-Qubit Systems

Shanidev Ambadas Sontakke

This paper explores the use of machine learning techniques for detecting quantum entanglement in two-qubit systems. A dataset of randomly generated quantum states was constructed and labeled using the Positive Partial Transpose (PPT) criterion. Several supervised learning models, including Random Forest and Multi-Layer Perceptron neural networks, were trained to classify quantum states as entangled or separable. The results show that machine learning models can effectively learn patterns from quantum state data, while also highlighting the impact of dataset imbalance on classification performance. This study demonstrates the potential of machine learning as a complementary tool for quantum entanglement detection and provides insights into the challenges and opportunities of integrating artificial intelligence with quantum physics.

•Jan 24, 2026•0 citations

Entanglement detection in pure states with a quantum classifier algorithm

Joab M. Varela

Entangled states proved to be an essential resource for information processing, however, its classification is still an open problem. The objective of this work is to apply machine learning methods based on distance metrics to make a quantum state classification. The classification method implementation was made using classical and quantum algorithms also comparing the performance and efficiency of both. However, it should be noted that all quantum computation processes made in this work used simulators provided by the SDK Qiskit. No real quantum computers were used to implement the quantum methods due to the qubit quantity that exceeds the available open-access quantum computers of the IBM Q-Experience. The classical results obtained in this work make a good classification of quantum states with a precision rate between 70% and 80%. The quantum predictions may have a lower precision, due to some simplifications made in the data pre-processing step, showing that quantum algorithms for entanglement classification probably will require a higher number of qubits than the currently available ones.

•Dec 14, 2023•0 citations

Quantum Machine Learning with Entanglement Resource Optimization

Jincheng Zhang

This paper investigates the potential of optimizing entanglement resources within quantum machine learning (QML) algorithms. Traditional approaches often treat entanglement as a readily available, cost-free resource. However, this research posits that strategic management and optimization of entanglement are crucial for significantly enhancing the performance and accuracy of QML models. The core concept involves building a quantum machine learning model, analyzing the algorithm's entanglement requirements, and then employing optimization techniques – specifically, quantum annealing-inspired algorithms – to determine the optimal allocation of entanglement. This approach aims to improve computational efficiency and overall accuracy by leveraging entanglement more effectively. We demonstrate, through theoretical analysis and algorithmic design, that a deliberate focus on entanglement resource optimization can represent a transformative step in advancing the field of quantum machine learning. The results suggest that entanglement, when properly managed, is not merely a byproduct of quantum computation but a key strategic element for achieving superior QML performance.

•Sep 7, 2026•0 citations
Classifying states as entangled or separable is a fundamental, but expensive task. This paper presents a method, the forest algorithm, to improve the amount of resources needed to detect entanglement. Starting from 'optimized' methods for using geometric criterion to detect entanglement, specific steps are replaced with machine learning models. Tests using numerical simulations indicate that the model is able to declare a state as entangled in fewer steps compared to existing methods. This improvement is achieved without affecting the correctness of the original algorithm.
Detection of entanglement is an indispensable step to practical quantum computation and communication. Compared with the conventional entanglement witness method based on fidelity, we propose a flexible, machine learning assisted entanglement detection protocol that is robust to different types of noises and sample efficient. In this protocol, an entanglement classifier for a generic entangled state is obtained by training a classical machine learning model with a synthetic dataset. The dataset contains classical features of two types of states and their labels (either entangled or separable). The classical features of a state, which are expectation values of a set of k-local Pauli observables, are estimated sample-efficiently by the classical shadow method. In the numerical simulation, our classifier can detect the entanglement of 4-qubit GHZ states with coherent noise and W states mixed with large white noise, with high accuracy.
The problem of determining whether a given quantum state is entangled lies at the heart of quantum information processing. Despite the many methods---such as the positive partial transpose criterion and the kkk-symmetric extendibility criterion---to tackle this problem, none of them enables a general, practical solution due to the problem's NP-hard complexity. Explicitly, separable states form a high-dimensional convex set of vastly complicated structures. In this work, we build a different separability-entanglement classifier underpinned by machine learning techniques. We use standard tools from machine learning to learn the entanglement feature of arbitrary given quantum states. We perform substantial numerical tests on two-qubit and two-qutrit systems, and the results indicate that our method can outperform the existing methods in generic cases in terms of both speed and accuracy. This opens up avenues to explore quantum entanglement via the machine learning approach.
We present a new technique to reduce the expected number of measurements to declare an unknown quantum state as entangled. Our method is based on the geometric criterion and so requires only local Pauli measurements. Using concentration of measure, we provide a heuristic which allows us to reinterpret a previous decision tree algorithm due to Laskowski et al and that forms the basis for our new algorithm. Numerical simulations show that for three to six qubits we use fewer measurements than either the trivial algorithm or the decision tree algorithm. In addition, our method is easy to construct, assumes no prior knowledge of the system and works for any number of qubits.
This paper explores the use of machine learning techniques for detecting quantum entanglement in two-qubit systems. A dataset of randomly generated quantum states was constructed and labeled using the Positive Partial Transpose (PPT) criterion. Several supervised learning models, including Random Forest and Multi-Layer Perceptron neural networks, were trained to classify quantum states as entangled or separable. The results show that machine learning models can effectively learn patterns from quantum state data, while also highlighting the impact of dataset imbalance on classification performance. This study demonstrates the potential of machine learning as a complementary tool for quantum entanglement detection and provides insights into the challenges and opportunities of integrating artificial intelligence with quantum physics.
Entangled states proved to be an essential resource for information processing, however, its classification is still an open problem. The objective of this work is to apply machine learning methods based on distance metrics to make a quantum state classification. The classification method implementation was made using classical and quantum algorithms also comparing the performance and efficiency of both. However, it should be noted that all quantum computation processes made in this work used simulators provided by the SDK Qiskit. No real quantum computers were used to implement the quantum methods due to the qubit quantity that exceeds the available open-access quantum computers of the IBM Q-Experience. The classical results obtained in this work make a good classification of quantum states with a precision rate between 70% and 80%. The quantum predictions may have a lower precision, due to some simplifications made in the data pre-processing step, showing that quantum algorithms for entanglement classification probably will require a higher number of qubits than the currently available ones.
This paper investigates the potential of optimizing entanglement resources within quantum machine learning (QML) algorithms. Traditional approaches often treat entanglement as a readily available, cost-free resource. However, this research posits that strategic management and optimization of entanglement are crucial for significantly enhancing the performance and accuracy of QML models. The core concept involves building a quantum machine learning model, analyzing the algorithm's entanglement requirements, and then employing optimization techniques – specifically, quantum annealing-inspired algorithms – to determine the optimal allocation of entanglement. This approach aims to improve computational efficiency and overall accuracy by leveraging entanglement more effectively. We demonstrate, through theoretical analysis and algorithmic design, that a deliberate focus on entanglement resource optimization can represent a transformative step in advancing the field of quantum machine learning. The results suggest that entanglement, when properly managed, is not merely a byproduct of quantum computation but a key strategic element for achieving superior QML performance.