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

Quantum-enhanced classification: an empirical study of quantum support vector machines using the iris and wine datasets

Deepak Ranga, Sunil Prajapat, Pankaj Kumar, Zahid Akhtar, Mohammed Al-Khalidi

Published Sep 17, 2025• 5 citations
Publisher

Abstract

Abstract Quantum computing has demonstrated a potential advantage in advancing artificial intelligence and machine learning applications. Both disciplines leverage higher-dimensional computation that relies on complex linear algebra operations. Quantum Support Vector Machines (QSVMs) uses quantum computation principles to enhance classification performance over traditional SVMs. This paper studies QSVMs applied to the Iris and Wine datasets by exploring various quantum encoding methods, including amplitude encoding, ZZFeatureMap, and PauliFeatureMap, within IBM’s Qiskit framework. These encoding methods enable QSVMs to utilize quantum phenomena like superposition and entanglement to transform classical data into quantum states to increase computational efficiency and accuracy in classification tasks. Numerical results indicate that QSVMs with amplitude encoding with combination of ZZFeatureMap achieve higher classification accuracy than traditional techniques. Also, this study assess the current performance of Noisy Intermediate-Scale Quantum (NISQ) devices to highlight the need for further optimization and advancements in quantum data encoding approches. These findings provide important insights into the application of QSVMs and their potential to address a range of classification problems effectively.

DOI
10.1088/1402-4896/ae0831

Related papers

Combining Dimensionality Reduction and Feature Map in Quantum Support Vector Machines

Chien‐Cheng Tseng, Su‐Ling Lee

Quantum support vector machines (QSVMs) offer a promising bridge between classical machine learning and quantum advantage by leveraging high-dimensional quantum feature spaces. However, practical implementation is often constrained by limited qubit resources, requiring efficient data representation. This paper evaluates the synergistic effects of combining various dimensionality reduction (DR) methods with different entanglement strategies in the quantum feature map. By investigating the influence of these combinations on classification accuracy, we identify good configurations for designing superior QSVM classifiers. Using the iris flower and wine datasets taken from scikit-learn, our experiments provide empirical insights into selecting the most effective DR-entanglement pairs, offering a framework for obtaining better classification performance within current hardware constraints.

IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)•Jul 1, 2026•0 citations

Variational Quantum Linear Solver Enhanced Quantum Support Vector Machine

Jianming Yi, Kalyani Suresh, Ali Moghiseh +1 more

Quantum Support Vector Machines (QSVM) play a vital role in using quantum resources for supervised machine learning tasks, such as classification. However, current methods are strongly limited in terms of scalability on Noisy Intermediate Scale Quantum (NISQ) devices. In this work, we propose a novel approach called the Variational Quantum Linear Solver (VQLS) enhanced QSVM. This is built upon our idea of utilizing the variational quantum linear solver to solve system of linear equations of a Least Squares-SVM on a NISQ device. The implementation of our approach is evaluated by an extensive series of numerical experiments with the Iris dataset, which consists of three distinct iris plant species. Based on this, we explore the effectiveness of our algorithm by constructing a classifier capable of classification in a feature space ranging from one to seven dimensions. Furthermore, we exploit both classical and quantum computing for various subroutines of our algorithm, and effectively mitigate challenges associated with the implementation. These include significant improvement in the trainability of the variational ansatz and notable reductions in run-time for cost calculations. Based on the numerical experiments, our approach exhibits the capability of identifying a separating hyperplane in an 8-dimensional feature space. Moreover, it consistently demonstrated strong performance across various instances with the same dataset.

arXiv:2309.07770•Advances in Artificial Intelligence and Machine Learning•Jan 1, 2024•5 citations

Improving Data Encoding for Enhanced AI Performance in Complex Datasets via Quantum Feature Space Mapping: Harnessing Quantum Algorithms

Gurpreet Singh Walia, Sathiya Priya S, KV Karthikeya +3 more

The purpose of this study is to investigate the potential for quantum feature space mapping to be utilized in the enhancement of data encoding approaches for artificial intelligence (AI) systems that are capable of managing complicated datasets. Traditional artificial intelligence models frequently face challenges when confronted with the high-dimensionality and non-linearity of such datasets. This can hinder their performance in areas such as pattern recognition, optimization, and predictive modeling. Quantum computing, which is able to make use of quantum superposition and entanglement, provides a method that is revolutionary in nature by means of quantum feature space mapping. By encoding data into quantum states, this technology enables the construction of feature spaces that are tenfold bigger than those that would be possible in classical conditions. This makes it much simpler to differentiate between intricate patterns that would otherwise be indistinguishable. The purpose of this research is to investigate the application of quantum algorithms, such as Quantum Support Vector Machines (QSVM) and Variational Quantum Classifiers (VQC), with the intention of enhancing the capacity of artificial intelligence to learn from complex and high-dimensional data. We demonstrate that quantum feature space mapping leads to more efficient and accurate data classification, regression, and clustering tasks by comparing the performance of quantum-enhanced artificial intelligence models to that of their classical counterparts on difficult datasets. Additionally, the research addresses important difficulties, such as the constraints of the quantum hardware that is now available and the requirement for quantum circuits that are scalable. Quantum computing has the potential to improve the performance of artificial intelligence in the management of complicated, high-dimensional data, which may ultimately pave the way for advances in domains such as genetics, finance, and cryptography. This work shows that quantum computing has this potential.

International Conference on Pervasive Computational Technologies (ICPCT)•Feb 8, 2025•11 citations

Investigation of Quantum Support Vector Machine for Classification in NISQ era

Anekait Kariya, Bikash K. Behera

Quantum machine learning is at the crossroads of two of the most exciting current areas of research; quantum computing and classical machine learning. It explores the interaction between quantum computing and machine learning, investigating how results and techniques from one field can be used to solve the problems of the other. Here, we investigate quantum support vector machine (QSVM) algorithm and its circuit version on present quantum computers. We propose a general encoding procedure extending QSVM algorithm, which would allow one to feed vectors with higher dimension in the training-data oracle of QSVM. We compute the efficiency of the QSVM circuit implementation method by encoding training and testing data sample in quantum circuits and running them on quantum simulator and real chip for two datasets; 6/9 and banknote. We highlight the technical difficulties one would face while applying the QSVM algorithm on current NISQ era devices. Then we propose a new method to classify these datasets with enhanced efficiencies for the above datasets both on simulator and real chips.

arXiv:2112.06912•Dec 13, 2021•38 citations

Analysis of Quantum SVM and KNN on Azure Quantum

Savita Kumari Sheoran, Vikesh Yadav, Rakesh Kumar Sheoran

Integrating quantum computing with machine learning proposes promising advancement by harnessing quantum parallelism and entanglement to enhance computational efficiency. This study investigates the implementation of a quantum support vector machine and quantum k nearest neighbor using azure quantum Ionq and Quantinuum simulators, utilizing Z, ZZ and Pauli feature maps to transform traditional data into quantum states, enabling the quantum enhanced learning. Four datasets are being carried out for this experiment: iris, wine, Indian liver patient and Rain dataset. To assess classification effectiveness, model performance is assessed using accuracy, F1 score, precision and recall. The findings thoroughly examine the influence of quantum simulators on quantum model performance, emphasizing the compromises of computational feasibility. This research contributes to the ongoing development of quantum machine learning by evaluating its practical applicability and current limitations.

International Conference on Pervasive Computing and Social Networking (ICPCSN)•May 14, 2025•0 citations

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•1 citation
Abstract Quantum computing has demonstrated a potential advantage in advancing artificial intelligence and machine learning applications. Both disciplines leverage higher-dimensional computation that relies on complex linear algebra operations. Quantum Support Vector Machines (QSVMs) uses quantum computation principles to enhance classification performance over traditional SVMs. This paper studies QSVMs applied to the Iris and Wine datasets by exploring various quantum encoding methods, including amplitude encoding, ZZFeatureMap, and PauliFeatureMap, within IBM’s Qiskit framework. These encoding methods enable QSVMs to utilize quantum phenomena like superposition and entanglement to transform classical data into quantum states to increase computational efficiency and accuracy in classification tasks. Numerical results indicate that QSVMs with amplitude encoding with combination of ZZFeatureMap achieve higher classification accuracy than traditional techniques. Also, this study assess the current performance of Noisy Intermediate-Scale Quantum (NISQ) devices to highlight the need for further optimization and advancements in quantum data encoding approches. These findings provide important insights into the application of QSVMs and their potential to address a range of classification problems effectively.
Quantum support vector machines (QSVMs) offer a promising bridge between classical machine learning and quantum advantage by leveraging high-dimensional quantum feature spaces. However, practical implementation is often constrained by limited qubit resources, requiring efficient data representation. This paper evaluates the synergistic effects of combining various dimensionality reduction (DR) methods with different entanglement strategies in the quantum feature map. By investigating the influence of these combinations on classification accuracy, we identify good configurations for designing superior QSVM classifiers. Using the iris flower and wine datasets taken from scikit-learn, our experiments provide empirical insights into selecting the most effective DR-entanglement pairs, offering a framework for obtaining better classification performance within current hardware constraints.
Quantum Support Vector Machines (QSVM) play a vital role in using quantum resources for supervised machine learning tasks, such as classification. However, current methods are strongly limited in terms of scalability on Noisy Intermediate Scale Quantum (NISQ) devices. In this work, we propose a novel approach called the Variational Quantum Linear Solver (VQLS) enhanced QSVM. This is built upon our idea of utilizing the variational quantum linear solver to solve system of linear equations of a Least Squares-SVM on a NISQ device. The implementation of our approach is evaluated by an extensive series of numerical experiments with the Iris dataset, which consists of three distinct iris plant species. Based on this, we explore the effectiveness of our algorithm by constructing a classifier capable of classification in a feature space ranging from one to seven dimensions. Furthermore, we exploit both classical and quantum computing for various subroutines of our algorithm, and effectively mitigate challenges associated with the implementation. These include significant improvement in the trainability of the variational ansatz and notable reductions in run-time for cost calculations. Based on the numerical experiments, our approach exhibits the capability of identifying a separating hyperplane in an 8-dimensional feature space. Moreover, it consistently demonstrated strong performance across various instances with the same dataset.
The purpose of this study is to investigate the potential for quantum feature space mapping to be utilized in the enhancement of data encoding approaches for artificial intelligence (AI) systems that are capable of managing complicated datasets. Traditional artificial intelligence models frequently face challenges when confronted with the high-dimensionality and non-linearity of such datasets. This can hinder their performance in areas such as pattern recognition, optimization, and predictive modeling. Quantum computing, which is able to make use of quantum superposition and entanglement, provides a method that is revolutionary in nature by means of quantum feature space mapping. By encoding data into quantum states, this technology enables the construction of feature spaces that are tenfold bigger than those that would be possible in classical conditions. This makes it much simpler to differentiate between intricate patterns that would otherwise be indistinguishable. The purpose of this research is to investigate the application of quantum algorithms, such as Quantum Support Vector Machines (QSVM) and Variational Quantum Classifiers (VQC), with the intention of enhancing the capacity of artificial intelligence to learn from complex and high-dimensional data. We demonstrate that quantum feature space mapping leads to more efficient and accurate data classification, regression, and clustering tasks by comparing the performance of quantum-enhanced artificial intelligence models to that of their classical counterparts on difficult datasets. Additionally, the research addresses important difficulties, such as the constraints of the quantum hardware that is now available and the requirement for quantum circuits that are scalable. Quantum computing has the potential to improve the performance of artificial intelligence in the management of complicated, high-dimensional data, which may ultimately pave the way for advances in domains such as genetics, finance, and cryptography. This work shows that quantum computing has this potential.
Quantum machine learning is at the crossroads of two of the most exciting current areas of research; quantum computing and classical machine learning. It explores the interaction between quantum computing and machine learning, investigating how results and techniques from one field can be used to solve the problems of the other. Here, we investigate quantum support vector machine (QSVM) algorithm and its circuit version on present quantum computers. We propose a general encoding procedure extending QSVM algorithm, which would allow one to feed vectors with higher dimension in the training-data oracle of QSVM. We compute the efficiency of the QSVM circuit implementation method by encoding training and testing data sample in quantum circuits and running them on quantum simulator and real chip for two datasets; 6/9 and banknote. We highlight the technical difficulties one would face while applying the QSVM algorithm on current NISQ era devices. Then we propose a new method to classify these datasets with enhanced efficiencies for the above datasets both on simulator and real chips.
Integrating quantum computing with machine learning proposes promising advancement by harnessing quantum parallelism and entanglement to enhance computational efficiency. This study investigates the implementation of a quantum support vector machine and quantum k nearest neighbor using azure quantum Ionq and Quantinuum simulators, utilizing Z, ZZ and Pauli feature maps to transform traditional data into quantum states, enabling the quantum enhanced learning. Four datasets are being carried out for this experiment: iris, wine, Indian liver patient and Rain dataset. To assess classification effectiveness, model performance is assessed using accuracy, F1 score, precision and recall. The findings thoroughly examine the influence of quantum simulators on quantum model performance, emphasizing the compromises of computational feasibility. This research contributes to the ongoing development of quantum machine learning by evaluating its practical applicability and current limitations.
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.