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:2003.07031 · Quantum Science and Technology

Finding semi-optimal measurements for entanglement detection using autoencoder neural networks

Mohammad Yosefpor, Mohammad Reza Mostaan, Sadegh Raeisi

Published Jul 6, 2020• 14 citations
arXivHTMLPDF

Abstract

Abstract Entanglement is one of the key resources of quantum information science which makes identification of entangled states essential to a wide range of quantum technologies and phenomena. This problem is however both computationally and experimentally challenging. Here we use autoencoder neural networks to find semi-optimal set of incomplete measurements that are most informative for the detection of entangled states . We show that it is possible to find high-performance entanglement detectors with as few as three measurements. Also, with the complete information of the state, we develop a neural network that can identify all two-qubits entangled states almost perfectly. This result paves the way for automatic development of efficient entanglement witnesses and entanglement detection using machine learning techniques.

DOI
10.1088/2058-9565/aba34c

Related papers

Accuracy of Entanglement Detection via Artificial Neural Networks and Human-Designed Entanglement Witnesses

Jan Roik, Karol Bartkiewicz, Antonín Černoch +1 more

The detection of entangled states is essential in both fundamental and applied quantum physics. However, this task proves to be challenging, especially for general quantum states. One can execute full state tomography but this method is time demanding, especially in complex systems. Other approaches use entanglement witnesses: these methods tend to be less demanding but lack reliability. Here, we demonstrate that artificial neural networks (ANNs) provide a balance between the two approaches. In this paper, we make a comparison of ANN performance with witness-based methods for random general two-qubit quantum states without any prior information on the states. Furthermore, we apply our approach to a real experimental data set.

arXiv:2011.11340•Physical Review Applied•May 4, 2021•27 citations

Detecting quantum entanglement with unsupervised learning

Yiwei Chen, Yu Pan, Guofeng Zhang +1 more

Abstract Quantum properties, such as entanglement and coherence, are indispensable resources in various quantum information processing tasks. However, there still lacks an efficient and scalable way to detecting these useful features especially for high-dimensional and multipartite quantum systems. In this work, we exploit the convexity of samples without the desired quantum features and design an unsupervised machine learning method to detect the presence of such features as anomalies. Particularly, in the context of entanglement detection, we propose a complex-valued neural network composed of pseudo-siamese network and generative adversarial net, and then train it with only separable states to construct non-linear witnesses for entanglement. It is shown via numerical examples, ranging from two-qubit to ten-qubit systems, that our network is able to achieve high detection accuracy which is above 97.5% on average. Moreover, it is capable of revealing rich structures of entanglement, such as partial entanglement among subsystems. Our results are readily applicable to the detection of other quantum resources such as Bell nonlocality and steerability, and thus our work could provide a powerful tool to extract quantum features hidden in multipartite quantum data.

arXiv:2103.04804•Quantum Science and Technology•Oct 19, 2021•65 citations

Entanglement detection with artificial neural networks

Naema Asif, Uman Khalid, Awais Khan +2 more

Quantum entanglement is one of the essential resources involved in quantum information processing tasks. However, its detection for usage remains a challenge. The Bell-type inequality for relative entropy of coherence serves as an entanglement witness for pure entangled states. However, it does not perform reliably for mixed entangled states. This paper constructs a classifier by employing the relationship between coherence and entanglement for supervised machine learning methods. This method encodes multiple Bell-type inequalities for the relative entropy of coherence into an artificial neural network to detect the entangled and separable states in a quantum dataset.

Scientific Reports•Jan 28, 2023•52 citations

Finding efficient observable operators in entanglement detection via convolutional neural network

Zi-Qi Lian, You-Yang Zhou, Liujun Wang +1 more

In quantum information, it is of high importance to efficiently detect entanglement. Generally, it needs quantum tomography to obtain state density matrix. However, it would consumes a lot of measurement resources, and the key is how to reduce the consumption. In this paper, we discovered the relationship between convolutional layer of artificial neural network and the average value of an observable operator in quantum mechanics. Then we devise a branching convolutional neural network which can be applied to detect entanglement in 2-qubit quantum system. Here, we detect the entanglement of Werner state, generalized Werner state and general 2-qubit states, and observable operators which are appropriate for detection can be automatically found. Beside, compared with privious works, our method can achieve higher accuracy with fewer measurements for quantum states with specific form. The results show that the convolutional neural network is very useful for efficiently detecting quantum entanglement.

arXiv:2205.13376•May 26, 2022•1 citation

Sensitivity versus selectivity in entanglement detection via collective witnesses

Vojtěch Trávníček, Jan Roik, Karol Bartkiewicz +3 more

In this paper, we introduce a supervised learning technique that harnesses artificial neural networks, along with the outcomes of collective entanglement measurements, to estimate the negativity of quantum states in two-qubit and qubit-qutrit systems. The resulting deep-learned collective entanglement witnesses offer the unique capability of continuous sensitivity and selectivity tuning. This instrument enables us to explore the tradeoff between sensitivity and selectivity in entanglement detection, a dimension not accessible to previously employed analytical witnesses. In particular, we demonstrate that there are experimentally cost-effective methods (in terms of the number of measurements) where sensitivity can be significantly improved at a slight expense of the selectivity of entanglement detection. This chosen approach is also favored due to its high generality and potential for superior performance compared to other types of entanglement witnesses. Our findings may pave the way for the development of more efficient and accurate entanglement detection methods in complex quantum systems, especially when considering realistic experimental imperfections. Published by the American Physical Society 2024

arXiv:2307.08293•Physical Review Research•Jul 11, 2024•6 citations

Low resource entanglement classification from neural network interpretability

A. García-Velo, R. Puebla, Y. Ban +2 more

Entanglement is a central resource in quantum information and quantum technologies, yet its characterization remains challenging due to both theoretical complexity and measurement requirements. Machine learning has emerged as a promising alternative, enabling entanglement characterization from incomplete measurement data, however model interpretability remains a challenge. In this work, we introduce a unified and interpretable framework for SLOCC entanglement classification of two- and three-qubit states, encompassing both pure and mixed states. We train dense and convolutional neural networks on Pauli-measurement outcomes, provide design guidelines for each architecture, and systematically compare their performance across types of states. To interpret the models, we compute Shapley values to quantify the contribution of each measurement, analyze measurement-importance patterns across different systems, and use these insights to guide a measurement-reduction scheme. Accuracy-versus-measurement curves and comparisons with analytical entanglement criteria demonstrate the minimal resources required for reliable classification and highlight both the capabilities and limitations of Shapley-based interpretability when using machine learning models for entanglement detection and classification.

quant-pharXiv:2602.04366•Feb 5, 2026•0 citations
Abstract Entanglement is one of the key resources of quantum information science which makes identification of entangled states essential to a wide range of quantum technologies and phenomena. This problem is however both computationally and experimentally challenging. Here we use autoencoder neural networks to find semi-optimal set of incomplete measurements that are most informative for the detection of entangled states . We show that it is possible to find high-performance entanglement detectors with as few as three measurements. Also, with the complete information of the state, we develop a neural network that can identify all two-qubits entangled states almost perfectly. This result paves the way for automatic development of efficient entanglement witnesses and entanglement detection using machine learning techniques.
The detection of entangled states is essential in both fundamental and applied quantum physics. However, this task proves to be challenging, especially for general quantum states. One can execute full state tomography but this method is time demanding, especially in complex systems. Other approaches use entanglement witnesses: these methods tend to be less demanding but lack reliability. Here, we demonstrate that artificial neural networks (ANNs) provide a balance between the two approaches. In this paper, we make a comparison of ANN performance with witness-based methods for random general two-qubit quantum states without any prior information on the states. Furthermore, we apply our approach to a real experimental data set.
Abstract Quantum properties, such as entanglement and coherence, are indispensable resources in various quantum information processing tasks. However, there still lacks an efficient and scalable way to detecting these useful features especially for high-dimensional and multipartite quantum systems. In this work, we exploit the convexity of samples without the desired quantum features and design an unsupervised machine learning method to detect the presence of such features as anomalies. Particularly, in the context of entanglement detection, we propose a complex-valued neural network composed of pseudo-siamese network and generative adversarial net, and then train it with only separable states to construct non-linear witnesses for entanglement. It is shown via numerical examples, ranging from two-qubit to ten-qubit systems, that our network is able to achieve high detection accuracy which is above 97.5% on average. Moreover, it is capable of revealing rich structures of entanglement, such as partial entanglement among subsystems. Our results are readily applicable to the detection of other quantum resources such as Bell nonlocality and steerability, and thus our work could provide a powerful tool to extract quantum features hidden in multipartite quantum data.
Quantum entanglement is one of the essential resources involved in quantum information processing tasks. However, its detection for usage remains a challenge. The Bell-type inequality for relative entropy of coherence serves as an entanglement witness for pure entangled states. However, it does not perform reliably for mixed entangled states. This paper constructs a classifier by employing the relationship between coherence and entanglement for supervised machine learning methods. This method encodes multiple Bell-type inequalities for the relative entropy of coherence into an artificial neural network to detect the entangled and separable states in a quantum dataset.
In quantum information, it is of high importance to efficiently detect entanglement. Generally, it needs quantum tomography to obtain state density matrix. However, it would consumes a lot of measurement resources, and the key is how to reduce the consumption. In this paper, we discovered the relationship between convolutional layer of artificial neural network and the average value of an observable operator in quantum mechanics. Then we devise a branching convolutional neural network which can be applied to detect entanglement in 2-qubit quantum system. Here, we detect the entanglement of Werner state, generalized Werner state and general 2-qubit states, and observable operators which are appropriate for detection can be automatically found. Beside, compared with privious works, our method can achieve higher accuracy with fewer measurements for quantum states with specific form. The results show that the convolutional neural network is very useful for efficiently detecting quantum entanglement.
In this paper, we introduce a supervised learning technique that harnesses artificial neural networks, along with the outcomes of collective entanglement measurements, to estimate the negativity of quantum states in two-qubit and qubit-qutrit systems. The resulting deep-learned collective entanglement witnesses offer the unique capability of continuous sensitivity and selectivity tuning. This instrument enables us to explore the tradeoff between sensitivity and selectivity in entanglement detection, a dimension not accessible to previously employed analytical witnesses. In particular, we demonstrate that there are experimentally cost-effective methods (in terms of the number of measurements) where sensitivity can be significantly improved at a slight expense of the selectivity of entanglement detection. This chosen approach is also favored due to its high generality and potential for superior performance compared to other types of entanglement witnesses. Our findings may pave the way for the development of more efficient and accurate entanglement detection methods in complex quantum systems, especially when considering realistic experimental imperfections. Published by the American Physical Society 2024
Entanglement is a central resource in quantum information and quantum technologies, yet its characterization remains challenging due to both theoretical complexity and measurement requirements. Machine learning has emerged as a promising alternative, enabling entanglement characterization from incomplete measurement data, however model interpretability remains a challenge. In this work, we introduce a unified and interpretable framework for SLOCC entanglement classification of two- and three-qubit states, encompassing both pure and mixed states. We train dense and convolutional neural networks on Pauli-measurement outcomes, provide design guidelines for each architecture, and systematically compare their performance across types of states. To interpret the models, we compute Shapley values to quantify the contribution of each measurement, analyze measurement-importance patterns across different systems, and use these insights to guide a measurement-reduction scheme. Accuracy-versus-measurement curves and comparisons with analytical entanglement criteria demonstrate the minimal resources required for reliable classification and highlight both the capabilities and limitations of Shapley-based interpretability when using machine learning models for entanglement detection and classification.