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

Physica Scripta

Unlocking quantum SVM potential: optimal feature map generation and feature selection

Sumaiyah Zahid, Muhammad Atif Tahir

Published Dec 12, 2024• 5 citations
Publisher

Abstract

Abstract The study proposes a mechanism to generate effective feature maps with optimal feature selection using the Tabu Search algorithm. It compares the performance of classical support vector machines (SVM), quantum support vector machines (QSVM) with only gate selection, and QSVM with both gate selection and feature selection (QSVM-FS) across various datasets. The results indicate that classical SVMs excel with several benchmark datasets, while QSVMs show superior performance on synthetic datasets with non-linear separability. Notably, QSVM-FS consistently outperforms QSVM without feature selection, highlighting the importance of feature selection in enhancing model accuracy. These findings suggest that while both quantum and classical SVMs have unique advantages, quantum methods offer particular benefits in specific scenarios. In the NISQ era, classical simulations are a primary tool for assessing quantum experiments, though they face challenges such as design impacts, limited scales, and biases. Ultimately, no definitive winner exists between quantum and classical methods, as both have their own strengths.

DOI
10.1088/1402-4896/ad9e39

Related papers

Why Classical-Quantum Machine Learning Works Better Than Classical Machine Learning

Abdullah Md Raihan Chy, Md. Farhan Shahriyar

Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris$(100 \%)$and Wine$(92 \%)$. All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.

IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)•Apr 16, 2026•0 citations

Investigating Quantum Feature Maps in Quantum Support Vector Machines for Lung Cancer Classification

Achraf Toufah, MA Kadim, Moulay Youssef El Hafidi

Background: Classical algorithms often struggle with the high dimensionality of medical data critical for early lung cancer diagnosis. While Quantum Machine Learning (QML) offers enhanced pattern recognition capabilities, the impact of specific quantum feature encoding strategies on diagnostic accuracy remains underexplored.Methods: We evaluated Quantum Support Vector Machines (QSVM) using a dataset of 309 lung cancer patients, divided into six balanced subsets to mitigate class imbalance. Models were implemented on a qasm simulator, comparing three encoding strategies: ZFeatureMap, ZZFeatureMap, and PauliFeatureMap. Performance was assessed using standard classification metrics.Results: The choice of feature map significantly influenced model efficacy. The PauliFeatureMap outperformed other kernels, achieving 100% classification accuracy in three of the six subsets, whereas ZFeatureMap and ZZFeatureMap yielded lower predictive consistency.Conclusion: Quantum feature map selection is a decisive factor in QSVM performance. Specifically, the PauliFeatureMap demonstrates high separability for medical data, highlighting the potential of optimized quantum kernels to improve diagnostic precision.

Journal of Artificial Intelligence Research and Innovation•Dec 29, 2025•6 citations

An enhanced approach for predicting air pollution using quantum support vector machine

Omer Farooq, Maida Shahid, Shazia Arshad +5 more

The essence of quantum machine learning is to optimize problem-solving by executing machine learning algorithms on quantum computers and exploiting potent laws such as superposition and entanglement. Support vector machine (SVM) is widely recognized as one of the most effective classification machine learning techniques currently available. Since, in conventional systems, the SVM kernel technique tends to sluggish down and even fail as datasets become increasingly complex or jumbled. To compare the execution time and accuracy of conventional SVM classification to that of quantum SVM classification, the appropriate quantum features for mapping need to be selected. As the dataset grows complex, the importance of selecting an appropriate feature map that outperforms or performs as well as the classification grows. This paper utilizes conventional SVM to select an optimal feature map and benchmark dataset for predicting air quality. Experimental evidence demonstrates that the precision of quantum SVM surpasses that of classical SVM for air quality assessment. Using quantum labs from IBM's quantum computer cloud, conventional and quantum computing have been compared. When applied to the same dataset, the conventional SVM achieved an accuracy of 91% and 87% respectively, whereas the quantum SVM demonstrated an accuracy of 97% and 94% respectively for air quality prediction. The study introduces the use of quantum Support Vector Machines (SVM) for predicting air quality. It emphasizes the novel method of choosing the best quantum feature maps. Through the utilization of quantum-enhanced feature mapping, our objective is to exceed the constraints of classical SVM and achieve unparalleled levels of precision and effectiveness. We conduct precise experiments utilizing IBM's state-of-the-art quantum computer cloud to compare the performance of conventional and quantum SVM algorithms on a shared dataset.

Scientific Reports•Aug 22, 2024•38 citations

Assessment of Quantum Feature Map for Binary Forest Classification using QSVM

Sudikin Pramanik, Ashutosh Kumar Jha

Quantum Support Vector Machine (Quantum SVM) is a prominent algorithm in quantum machine learning. A key challenge in this field is the efficient mapping of classical data into a quantum feature space. Despite its significance, there is a lack of systematic studies identifying the most suitable feature map for remote sensing specfic classification tasks. This study bridges that gap by determining the optimal feature map for forest class identification, revealing the superior potential of the Pauli feature map in remote sensing data classification. By leveraging Pauli feature representations, Quantum SVMs enable more effective extraction of quantum-enhanced patterns from complex datasets, providing a robust framework for solving non-linear classification problems in quantum machine learning.

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)•Aug 3, 2025•0 citations

Quantum Machine Learning—An Overview

Kyriaki A. Tychola, Τheofanis Kalampokas, George A. Papakostas

Quantum computing has been proven to excel in factorization issues and unordered search problems due to its capability of quantum parallelism. This unique feature allows exponential speed-up in solving certain problems. However, this advantage does not apply universally, and challenges arise when combining classical and quantum computing to achieve acceleration in computation speed. This paper aims to address these challenges by exploring the current state of quantum machine learning and benchmarking the performance of quantum and classical algorithms in terms of accuracy. Specifically, we conducted experiments with three datasets for binary classification, implementing Support Vector Machine (SVM) and Quantum SVM (QSVM) algorithms. Our findings suggest that the QSVM algorithm outperforms classical SVM on complex datasets, and the performance gap between quantum and classical models increases with dataset complexity, as simple models tend to overfit with complex datasets. While there is still a long way to go in terms of developing quantum hardware with sufficient resources, quantum machine learning holds great potential in areas such as unsupervised learning and generative models. Moving forward, more efforts are needed to explore new quantum learning models that can leverage the power of quantum mechanics to overcome the limitations of classical machine learning.

Electronics•May 24, 2023•118 citations

Enhancing Crop Recommendation Accuracy using Quantum Support Vector Machines on Complex Agricultural Datasets

Varun S, Abirami S

Crop recommendation systems are very important in sustainable agriculture and yield optimization. Most of the traditional machine learning algorithms, such as SVM, do not work well on datasets for which there is a strong nonlinear relationship between the features such as soil parameters, climatic conditions and labels of crops. In this paper, we investigate the performance difference between classical SVM and Quantum Support Vector Machine (QSVM) when trained with highly complex, non-linear agriculture dataset. A synthetic non-linear dataset was constructed to mimic challenging real-world agriculture patterns, and is used to evaluate both the models fairly. Experimental results shows that classical SVM struggles to model deep feature dependencies, while QSVM significantly outperforms it by 10% increase in the accuracy due to the advantage of quantum feature encoding and high-dimensional Hilbert space mapping. This paper illustrates the potential benefits of quantum machine learning in different agricultural applications and indicates the advantages of quantum-enhanced models when dealing with challenging data sets.

International Conference on Emerging Trends in Advancements and Applications of Computational Intelligence Techniques (ETAACT)•Apr 10, 2026•0 citations
Abstract The study proposes a mechanism to generate effective feature maps with optimal feature selection using the Tabu Search algorithm. It compares the performance of classical support vector machines (SVM), quantum support vector machines (QSVM) with only gate selection, and QSVM with both gate selection and feature selection (QSVM-FS) across various datasets. The results indicate that classical SVMs excel with several benchmark datasets, while QSVMs show superior performance on synthetic datasets with non-linear separability. Notably, QSVM-FS consistently outperforms QSVM without feature selection, highlighting the importance of feature selection in enhancing model accuracy. These findings suggest that while both quantum and classical SVMs have unique advantages, quantum methods offer particular benefits in specific scenarios. In the NISQ era, classical simulations are a primary tool for assessing quantum experiments, though they face challenges such as design impacts, limited scales, and biases. Ultimately, no definitive winner exists between quantum and classical methods, as both have their own strengths.
Quantum machine learning has emerged as a promising paradigm that leverages quantum computational principles to potentially outperform classical approaches on specific learning tasks. This paper presents a comprehensive empirical investigation comparing Quantum Machine Learning (QML), specifically Quantum Support Vector Machines (QSVM) against Classical Machine Learning (CML) baselines including Logistic Regression, K Nearest Neighbors and classical SVMs. We implement quantum kernel methods using variational quantum circuits with angle embedding, IQP and ZZ feature maps on datasets exhibiting varying structural complexity. Our experiments on synthetic quantum generated datasets (Quantum Parity, Quantum Entanglement, Quantum Interference) demonstrate that QSVM achieves superior classification accuracy with improvements ranging from 2.9 % to 60 % over the best classical baselines achieving a 55.6 % overall win rate. Notably, on the Quantum Parity dataset, QSVM consistently outperformed all classical models across multiple configurations. On real-world benchmark datasets (Breast Cancer, Iris, Wine), QSVM Angle achieved 88% accuracy on Breast Cancer compared to 76% for classical SVM Linear a 15.8 % relative improvement while matching the best classical performance on Iris(100%)(100 \%)(100%)and Wine(92%)(92 \%)(92%). All experiments were conducted using quantum circuit simulation on classical hardware. These results provide empirical evidence that quantum kernel methods offer meaningful advantages over classical approaches on datasets with complex feature interactions. We discuss the theoretical foundations of these improvements including quantum feature space expressivity and kernel alignment.
Background: Classical algorithms often struggle with the high dimensionality of medical data critical for early lung cancer diagnosis. While Quantum Machine Learning (QML) offers enhanced pattern recognition capabilities, the impact of specific quantum feature encoding strategies on diagnostic accuracy remains underexplored.Methods: We evaluated Quantum Support Vector Machines (QSVM) using a dataset of 309 lung cancer patients, divided into six balanced subsets to mitigate class imbalance. Models were implemented on a qasm simulator, comparing three encoding strategies: ZFeatureMap, ZZFeatureMap, and PauliFeatureMap. Performance was assessed using standard classification metrics.Results: The choice of feature map significantly influenced model efficacy. The PauliFeatureMap outperformed other kernels, achieving 100% classification accuracy in three of the six subsets, whereas ZFeatureMap and ZZFeatureMap yielded lower predictive consistency.Conclusion: Quantum feature map selection is a decisive factor in QSVM performance. Specifically, the PauliFeatureMap demonstrates high separability for medical data, highlighting the potential of optimized quantum kernels to improve diagnostic precision.
The essence of quantum machine learning is to optimize problem-solving by executing machine learning algorithms on quantum computers and exploiting potent laws such as superposition and entanglement. Support vector machine (SVM) is widely recognized as one of the most effective classification machine learning techniques currently available. Since, in conventional systems, the SVM kernel technique tends to sluggish down and even fail as datasets become increasingly complex or jumbled. To compare the execution time and accuracy of conventional SVM classification to that of quantum SVM classification, the appropriate quantum features for mapping need to be selected. As the dataset grows complex, the importance of selecting an appropriate feature map that outperforms or performs as well as the classification grows. This paper utilizes conventional SVM to select an optimal feature map and benchmark dataset for predicting air quality. Experimental evidence demonstrates that the precision of quantum SVM surpasses that of classical SVM for air quality assessment. Using quantum labs from IBM's quantum computer cloud, conventional and quantum computing have been compared. When applied to the same dataset, the conventional SVM achieved an accuracy of 91% and 87% respectively, whereas the quantum SVM demonstrated an accuracy of 97% and 94% respectively for air quality prediction. The study introduces the use of quantum Support Vector Machines (SVM) for predicting air quality. It emphasizes the novel method of choosing the best quantum feature maps. Through the utilization of quantum-enhanced feature mapping, our objective is to exceed the constraints of classical SVM and achieve unparalleled levels of precision and effectiveness. We conduct precise experiments utilizing IBM's state-of-the-art quantum computer cloud to compare the performance of conventional and quantum SVM algorithms on a shared dataset.
Quantum Support Vector Machine (Quantum SVM) is a prominent algorithm in quantum machine learning. A key challenge in this field is the efficient mapping of classical data into a quantum feature space. Despite its significance, there is a lack of systematic studies identifying the most suitable feature map for remote sensing specfic classification tasks. This study bridges that gap by determining the optimal feature map for forest class identification, revealing the superior potential of the Pauli feature map in remote sensing data classification. By leveraging Pauli feature representations, Quantum SVMs enable more effective extraction of quantum-enhanced patterns from complex datasets, providing a robust framework for solving non-linear classification problems in quantum machine learning.
Quantum computing has been proven to excel in factorization issues and unordered search problems due to its capability of quantum parallelism. This unique feature allows exponential speed-up in solving certain problems. However, this advantage does not apply universally, and challenges arise when combining classical and quantum computing to achieve acceleration in computation speed. This paper aims to address these challenges by exploring the current state of quantum machine learning and benchmarking the performance of quantum and classical algorithms in terms of accuracy. Specifically, we conducted experiments with three datasets for binary classification, implementing Support Vector Machine (SVM) and Quantum SVM (QSVM) algorithms. Our findings suggest that the QSVM algorithm outperforms classical SVM on complex datasets, and the performance gap between quantum and classical models increases with dataset complexity, as simple models tend to overfit with complex datasets. While there is still a long way to go in terms of developing quantum hardware with sufficient resources, quantum machine learning holds great potential in areas such as unsupervised learning and generative models. Moving forward, more efforts are needed to explore new quantum learning models that can leverage the power of quantum mechanics to overcome the limitations of classical machine learning.
Crop recommendation systems are very important in sustainable agriculture and yield optimization. Most of the traditional machine learning algorithms, such as SVM, do not work well on datasets for which there is a strong nonlinear relationship between the features such as soil parameters, climatic conditions and labels of crops. In this paper, we investigate the performance difference between classical SVM and Quantum Support Vector Machine (QSVM) when trained with highly complex, non-linear agriculture dataset. A synthetic non-linear dataset was constructed to mimic challenging real-world agriculture patterns, and is used to evaluate both the models fairly. Experimental results shows that classical SVM struggles to model deep feature dependencies, while QSVM significantly outperforms it by 10% increase in the accuracy due to the advantage of quantum feature encoding and high-dimensional Hilbert space mapping. This paper illustrates the potential benefits of quantum machine learning in different agricultural applications and indicates the advantages of quantum-enhanced models when dealing with challenging data sets.