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:2606.04363 · Physica Scripta

Robust Steerability Classification via Key Feature Extraction and Matrix Structure Preservation

Yutao Xin, Huixian Meng, Zhongyan Li, Pu Wang

quant-phSubmitted Jun 3, 2026• Announced Jun 4, 2026• 0 citations
arXivHTMLPDF

Abstract

Generalization ability is essential for assessing the robustness of quantum steerability classifiers. In this work, we investigate robust steerability classification from the perspective of key feature extraction and matrix structure preservation. The dataset introduced in Phys. Rev. A 100, 022314 (2019) provides the training basis for the present work. With strictly unsteerable random states, T-diagonal states, and All-Versus-Nothing (AVN) states, we evaluate the generalization performance of support vector machines (SVMs), multilayer perceptrons (MLPs), and deep perceptron control classifiers(DPs) trained on full-information features. None of these classifiers perform consistently on T-diagonal or AVN states. Given that stochastic local operations and classical communication and local unitary transformations preserve steerability, we introduce a key feature that determines steerability. SVMs trained on this feature overcome the instability on T-diagonal states but still fail on AVN states. Moreover, this feature alone is insufficient for training robust neural-network-based steerability classifiers. Recognizing that flattening quantum states into one-dimensional vectors may destroy their intrinsic matrix structure, we introduce matrix versions of both features and train convolutional neural networks on them. The most robust overall performance among the tested classifiers is achieved only when the matrix structure is preserved and key features are extracted simultaneously. Finally, as an application, we employ the most robust classifiers to predict the number of projective measurements required to detect the steerability of axially symmetric states

Comments
12 pages,5 figures

Related papers

Machine learning for detecting steering in qutrit-pair states

Pu Wang, Zhongyan Li, Hui-Xian Meng

Only a few states in high-dimensional systems can be identified as (un)steerable using existing theoretical or experimental methods. We utilize semidefinite programming (SDP) to construct a dataset for steerability detection in qutrit-qutrit systems. For the full-information feature ${F}_{1}$, artificial neural networks achieve high classification accuracy and generalization, and perform better than the support vector machine. As feature engineering plays a pivotal role, we introduce a steering ellipsoidlike feature, ${F}_{2}$, which significantly enhances the performance of each of our models. To address quantum steering detection in isotropic states, partially entangled states, and random states, we explore, respectively, the most tailored feature and classifier. Given that the SDP method provides only a sufficient condition for steerability detection, we establish the first rigorously constructed, accurately labeled dataset based on theoretical foundations. This dataset enables models to exhibit outstanding accuracy and generalization capabilities, independent of the choice of features. As applications, we investigate the steerability boundaries of isotropic states and partially entangled states, discover new steerable states, and determine their parameter ranges. This work not only advances the application of machine learning for probing quantum steerability in high-dimensional systems but also deepens the theoretical understanding of quantum steerability itself.

arXiv:2502.11365•Physical Review A•Sep 8, 2025•2 citations

Improving Steerability Detection via an Aggregate Class Distribution Neural Network

Yuyang Hao, Kan He, Ying Zhang

In this paper, we establish an aggregate class distribution neural network (AGGNN) structure to determine whether an arbitrary two-qubit quantum state is steerable. Compared to the classification results obtained using a support vector machine (SVM) and a backpropagation neural network (BPNN), we obtain higher-accuracy quantum-steering classification models via the AGGNN, as well as steerability bounds of generalized Werner states, which are more similar to the theoretical bounds. In particular, when we only know partial information about the quantum states, higher-performance quantum-steering classifiers are obtained compared to those via SVM and BPNN.

Applied Sciences•Jul 4, 2023•1 citation

Detecting the steerability bounds of generalized Werner states via a backpropagation neural network

Jun Zhang, Kan He, Ying Zhang +4 more

We use an error backpropagation (BP) neural network to determine whether an arbitrary two-qubit quantum state is steerable and optimize the steerability bounds of the generalized Werner state. Results show that, regardless of how we select the features for the quantum states, we can use the BP neural network to construct several models to obtain high-performance quantum steering classifiers compared with the support vector machine. Moreover, we predict the steerability bounds of the generalized Werner states using the classifiers that are newly constructed by the BP neural network; that is, the predicted steerability bounds are closer to the theoretical bounds. In particular, high-performance quantum steering classifiers with partial information about the quantum states that we need to measure in only three fixed measurement directions are obtained.

arXiv:2110.13379•Physical Review A•Mar 3, 2022•19 citations

Do We Really Need Quantum Machine Learning?: A Multidimensional Empirical Study

Sudip Vhaduri, Ryan Gammon, Sayanton Dibbo

The rapid growth of computer vision and increasingly complex image recognition tasks has exposed fundamental computational limitations of classical machine learning models, motivating the exploration of quantum computing as an emerging new paradigm. This paper presents a comprehensive benchmarking study of classical and quantum machine learning models for image recognition on the MNIST handwritten digit dataset, evaluating both traditional models, a Classical Support Vector Machine (CSVM) and a Quantum Support Vector Machine (QSVM), and deep neural network models, a Classical Convolutional Neural Network (CCNN) and a Quantum Convolutional Neural Network (QCNN), across four performance dimensions: classification accuracy, computational runtime, parameter count, and memory requirements. Experiments are conducted as functions of both feature dimensionality and sample size, and across CPU and GPU execution environments, providing a controlled, multidimensional comparison to address gaps in prior work. For the SVM-based models, QSVM consistently outperforms CSVM in accuracy, reaching $\sim$ 0.90 versus $\sim$ 0.85 at 1,000 samples, with a higher computational cost. A feature count of 10 qubits and a sample size in the range of 200 -- 500 emerge as practical operating points that balance accuracy and runtime. For the neural network models, CCNN and QCNN achieve comparable classification accuracy, both exceeding 0.96 at 64 features and 60,000 samples, yet QCNN offers superior parameter and memory efficiency at higher feature counts, while incurring higher runtime. Across both model families, quantum models consistently outperform classical models by greater margins in accuracy as feature dimensionality or sample size increases.

cs.CVCross-listedarXiv:2605.27923•May 28, 2026•4 citations

Deep learning the hierarchy of steering measurement settings of qubit-pair states

Hongming Wang, Huan-Yu Ku, Jie-Yien Lin +1 more

Abstract Quantum steering has attracted increasing research attention because of its fundamental importance, as well as its applications in quantum information science. Here we leverage the power of the deep learning model to infer the steerability of quantum states with specific numbers of measurement settings, which form a hierarchical structure. A computational protocol consisting of iterative tests is constructed to overcome the optimization, meanwhile, generating the necessary training data. According to the responses of the well-trained models to the different physics-driven features encoding the states to be recognized, we can numerically conclude that the most compact characterization of the Alice-to-Bob steerability is Alice’s regularly aligned steering ellipsoid; whereas Bob’s ellipsoid is irrelevant. We have also provided an explanation to this result with the one-way stochastic local operations and classical communication. Additionally, our approach is versatile in revealing further insights into the hierarchical structure of quantum steering and detecting the hidden steerability.

arXiv:2306.05201•Communications Physics•Mar 1, 2024•21 citations

Machine learning detection of Gaussian steering in continuous-variable systems under data imbalance

Jie Guo, Taotao Yan, Jinchuan Hou +2 more

Gaussian steering in continuousvariable (CV) systems, as a quantum correlation between nonlocality and entanglement, is an important quantum resource. Rapid detection of Gaussian steering is a significant challenge in quantum information process. In this paper, we employ a combination of machine learning methods, including Support Vector Machine (SVM), Backpropagation Neural Network (BPNN) and Meta-Weight-Net Neural Network (MWN) to speed up the detection. An ensemble learning approach that integrates these methods is also utilized to increase the accuracy of detection. A computable Gaussian steering quantification [Formula: see text] introduced recently in [Phys. Rev. A 110, 052427] serves as a pivotal tool for labeling the samples. A key observation is that steerable Gaussian states are vastly outnumbered by unsteerable ones, particularly in configurations where the untrusted party possesses significantly more modes than the trusted party. This leads to a highly skewed distribution of sample states in the dataset. In response to this phenomenon and to make comparison, we propose the imbalance factor ξ and prepare three types of datasets to be trained: balanced datasets, naturally generated datasets and augmented datasets with [Formula: see text] via a data augmentation strategy. Numerical experiments for seven low modes scenarios reveal that the classifiers obtained by utilizing the ensemble learning method training on augmented dataset have the best overall performance, significantly improving generalization capabilities with low cost and high test accuracy, achieving detection times as fast as [Formula: see text] seconds, at least 100 times faster than calculating [Formula: see text]. The speed advantage of machine learning detection will be more obvious in the case of higher modes. Thus the approach is both efficient and reliable, offering valuable insights into the broader potential of machine learning applications in quantum information science and providing a robust framework for machine learning utilized to classification tasks, especially in data-imbalanced scenarios.

Scientific Reports•Jul 1, 2025•0 citations
Generalization ability is essential for assessing the robustness of quantum steerability classifiers. In this work, we investigate robust steerability classification from the perspective of key feature extraction and matrix structure preservation. The dataset introduced in Phys. Rev. A 100, 022314 (2019) provides the training basis for the present work. With strictly unsteerable random states, T-diagonal states, and All-Versus-Nothing (AVN) states, we evaluate the generalization performance of support vector machines (SVMs), multilayer perceptrons (MLPs), and deep perceptron control classifiers(DPs) trained on full-information features. None of these classifiers perform consistently on T-diagonal or AVN states. Given that stochastic local operations and classical communication and local unitary transformations preserve steerability, we introduce a key feature that determines steerability. SVMs trained on this feature overcome the instability on T-diagonal states but still fail on AVN states. Moreover, this feature alone is insufficient for training robust neural-network-based steerability classifiers. Recognizing that flattening quantum states into one-dimensional vectors may destroy their intrinsic matrix structure, we introduce matrix versions of both features and train convolutional neural networks on them. The most robust overall performance among the tested classifiers is achieved only when the matrix structure is preserved and key features are extracted simultaneously. Finally, as an application, we employ the most robust classifiers to predict the number of projective measurements required to detect the steerability of axially symmetric states
Only a few states in high-dimensional systems can be identified as (un)steerable using existing theoretical or experimental methods. We utilize semidefinite programming (SDP) to construct a dataset for steerability detection in qutrit-qutrit systems. For the full-information feature F1{F}_{1}F1​, artificial neural networks achieve high classification accuracy and generalization, and perform better than the support vector machine. As feature engineering plays a pivotal role, we introduce a steering ellipsoidlike feature, F2{F}_{2}F2​, which significantly enhances the performance of each of our models. To address quantum steering detection in isotropic states, partially entangled states, and random states, we explore, respectively, the most tailored feature and classifier. Given that the SDP method provides only a sufficient condition for steerability detection, we establish the first rigorously constructed, accurately labeled dataset based on theoretical foundations. This dataset enables models to exhibit outstanding accuracy and generalization capabilities, independent of the choice of features. As applications, we investigate the steerability boundaries of isotropic states and partially entangled states, discover new steerable states, and determine their parameter ranges. This work not only advances the application of machine learning for probing quantum steerability in high-dimensional systems but also deepens the theoretical understanding of quantum steerability itself.
In this paper, we establish an aggregate class distribution neural network (AGGNN) structure to determine whether an arbitrary two-qubit quantum state is steerable. Compared to the classification results obtained using a support vector machine (SVM) and a backpropagation neural network (BPNN), we obtain higher-accuracy quantum-steering classification models via the AGGNN, as well as steerability bounds of generalized Werner states, which are more similar to the theoretical bounds. In particular, when we only know partial information about the quantum states, higher-performance quantum-steering classifiers are obtained compared to those via SVM and BPNN.
We use an error backpropagation (BP) neural network to determine whether an arbitrary two-qubit quantum state is steerable and optimize the steerability bounds of the generalized Werner state. Results show that, regardless of how we select the features for the quantum states, we can use the BP neural network to construct several models to obtain high-performance quantum steering classifiers compared with the support vector machine. Moreover, we predict the steerability bounds of the generalized Werner states using the classifiers that are newly constructed by the BP neural network; that is, the predicted steerability bounds are closer to the theoretical bounds. In particular, high-performance quantum steering classifiers with partial information about the quantum states that we need to measure in only three fixed measurement directions are obtained.
The rapid growth of computer vision and increasingly complex image recognition tasks has exposed fundamental computational limitations of classical machine learning models, motivating the exploration of quantum computing as an emerging new paradigm. This paper presents a comprehensive benchmarking study of classical and quantum machine learning models for image recognition on the MNIST handwritten digit dataset, evaluating both traditional models, a Classical Support Vector Machine (CSVM) and a Quantum Support Vector Machine (QSVM), and deep neural network models, a Classical Convolutional Neural Network (CCNN) and a Quantum Convolutional Neural Network (QCNN), across four performance dimensions: classification accuracy, computational runtime, parameter count, and memory requirements. Experiments are conducted as functions of both feature dimensionality and sample size, and across CPU and GPU execution environments, providing a controlled, multidimensional comparison to address gaps in prior work. For the SVM-based models, QSVM consistently outperforms CSVM in accuracy, reaching ∼\sim∼ 0.90 versus ∼\sim∼ 0.85 at 1,000 samples, with a higher computational cost. A feature count of 10 qubits and a sample size in the range of 200 -- 500 emerge as practical operating points that balance accuracy and runtime. For the neural network models, CCNN and QCNN achieve comparable classification accuracy, both exceeding 0.96 at 64 features and 60,000 samples, yet QCNN offers superior parameter and memory efficiency at higher feature counts, while incurring higher runtime. Across both model families, quantum models consistently outperform classical models by greater margins in accuracy as feature dimensionality or sample size increases.
Abstract Quantum steering has attracted increasing research attention because of its fundamental importance, as well as its applications in quantum information science. Here we leverage the power of the deep learning model to infer the steerability of quantum states with specific numbers of measurement settings, which form a hierarchical structure. A computational protocol consisting of iterative tests is constructed to overcome the optimization, meanwhile, generating the necessary training data. According to the responses of the well-trained models to the different physics-driven features encoding the states to be recognized, we can numerically conclude that the most compact characterization of the Alice-to-Bob steerability is Alice’s regularly aligned steering ellipsoid; whereas Bob’s ellipsoid is irrelevant. We have also provided an explanation to this result with the one-way stochastic local operations and classical communication. Additionally, our approach is versatile in revealing further insights into the hierarchical structure of quantum steering and detecting the hidden steerability.
Gaussian steering in continuousvariable (CV) systems, as a quantum correlation between nonlocality and entanglement, is an important quantum resource. Rapid detection of Gaussian steering is a significant challenge in quantum information process. In this paper, we employ a combination of machine learning methods, including Support Vector Machine (SVM), Backpropagation Neural Network (BPNN) and Meta-Weight-Net Neural Network (MWN) to speed up the detection. An ensemble learning approach that integrates these methods is also utilized to increase the accuracy of detection. A computable Gaussian steering quantification [Formula: see text] introduced recently in [Phys. Rev. A 110, 052427] serves as a pivotal tool for labeling the samples. A key observation is that steerable Gaussian states are vastly outnumbered by unsteerable ones, particularly in configurations where the untrusted party possesses significantly more modes than the trusted party. This leads to a highly skewed distribution of sample states in the dataset. In response to this phenomenon and to make comparison, we propose the imbalance factor ξ and prepare three types of datasets to be trained: balanced datasets, naturally generated datasets and augmented datasets with [Formula: see text] via a data augmentation strategy. Numerical experiments for seven low modes scenarios reveal that the classifiers obtained by utilizing the ensemble learning method training on augmented dataset have the best overall performance, significantly improving generalization capabilities with low cost and high test accuracy, achieving detection times as fast as [Formula: see text] seconds, at least 100 times faster than calculating [Formula: see text]. The speed advantage of machine learning detection will be more obvious in the case of higher modes. Thus the approach is both efficient and reliable, offering valuable insights into the broader potential of machine learning applications in quantum information science and providing a robust framework for machine learning utilized to classification tasks, especially in data-imbalanced scenarios.