Classical machine learning, extensively utilized across diverse domains, faces limitations in speed, efficiency, parallelism, and processing of complex datasets. In contrast, quantum machine learning algorithms offer significant advantages, including exponentially faster computations, enhanced data handling capabilities, inherent parallelism, and improved optimization for complex problems. In this study, we used the entanglement enhanced quantum kernel in a quantum support vector machine to train complex respiratory datasets. Compared to classical algorithms, our findings reveal that quantum support vector machine (QSVM) performs better with higher accuracy (45%) for complex respiratory datasets while maintaining comparable performance with linear datasets in contrast to their classical counterparts executed on a 2-qubit system. Through our study, we investigate the efficacy of the QSVM-Kernel algorithm in harnessing the enhanced dimensionality of the quantum Hilbert space for effectively training complex datasets.Classical machine learning, extensively utilized across diverse domains, faces limitations in speed, efficiency, parallelism, and processing of complex datasets. In contrast, quantum machine learning algorithms offer significant advantages, including exponentially faster computations, enhanced data handling capabilities, inherent parallelism, and improved optimization for complex problems. In this study, we used the entanglement enhanced quantum kernel in a quantum support vector machine to train complex respiratory datasets. Compared to classical algorithms, our findings reveal that quantum support vector machine (QSVM) performs better with higher accuracy (45%) for complex respiratory datasets while maintaining comparable performance with linear datasets in contrast to their classical counterparts executed on a 2-qubit system. Through our study, we investigate the efficacy of the QSVM-Kernel algorithm in harnessing the enhanced dimensionality of the quantum Hilbert space for effectively training complex datasets.

APL QuantumFeb 10, 20258 citations

Quantum optimization for training support vector machines

Davide Anguita, Sandro Ridella, Fabio Rivieccio +1 more

Neural NetworksMay 19, 2003119 citations

NQ-SVM: Scalable Quantum Kernel Learning via Nyström-Based Support Vector Machines

Duong The Do, Srikanth Thudumu, Prem Prakash Jayaraman +1 more

Abstract Support vector machines (SVMs) are widely used for classification, but become computationally expensive as datasets grow and data become high-dimensional or nonlinearly separable. Quantum support vector machines (QSVMs) enhance the traditional SVMs by replacing conventional feature mappings with quantum-implemented embeddings that project data into high-dimensional Hilbert spaces, potentially improving expressive power and efficiency. However, training QSVMs on current noisy intermediate-scale quantum (NISQ) devices remains challenging, as constructing the quantum kernel matrix requires repeated circuit executions and scales quadratically with dataset size. We propose NQ-SVM , a hybrid quantum-classical method that incorporates the Nystr\"om approximation to enhance the scalability of QSVMs. By selecting a small set of landmark points, the Nystr\"om method yields a low-rank kernel approximation, reducing complexity from $(O(n^2))$ to $(O(nm))$ , while preserving the quantum advantages in handling high-dimensional, non-linear data. Extensive simulations demonstrate that NQ-SVM achieves comparable classification accuracy to classical SVMs and full QSVMs, while substantially reducing training time and kernel evaluation costs. These results underscore the potential of NQ-SVM as a scalable and practical hybrid framework for near-term quantum machine learning (QML).Abstract Support vector machines (SVMs) are widely used for classification, but become computationally expensive as datasets grow and data become high-dimensional or nonlinearly separable. Quantum support vector machines (QSVMs) enhance the traditional SVMs by replacing conventional feature mappings with quantum-implemented embeddings that project data into high-dimensional Hilbert spaces, potentially improving expressive power and efficiency. However, training QSVMs on current noisy intermediate-scale quantum (NISQ) devices remains challenging, as constructing the quantum kernel matrix requires repeated circuit executions and scales quadratically with dataset size. We propose NQ-SVM , a hybrid quantum-classical method that incorporates the Nystr\"om approximation to enhance the scalability of QSVMs. By selecting a small set of landmark points, the Nystr\"om method yields a low-rank kernel approximation, reducing complexity from $(O(n^2))$ to $(O(nm))$, while preserving the quantum advantages in handling high-dimensional, non-linear data. Extensive simulations demonstrate that NQ-SVM achieves comparable classification accuracy to classical SVMs and full QSVMs, while substantially reducing training time and kernel evaluation costs. These results underscore the potential of NQ-SVM as a scalable and practical hybrid framework for near-term quantum machine learning (QML).

Mar 3, 20260 citations

Quantum Enhanced Support Vector Machine with Instantaneous Quantum Polynomial Encoding for Improved Cyclone Classification

Sriadibhatla Sridevi, B Indira, Shivanya Shomir Dutta +2 more

The paradigm of classical machine learning has been greatly revolutionized by the integration of the quantum computing paradigm, which has made it possible to solve complicated issues that were previously unsolvable by conventional computers. One such problem is accurately classifying cyclones with minimal data samples and feature parameters. In this paper, we investigate the superior learning capabilities of the Instantaneous Quantum Polynomial Embedding-based kernel Support Vector Machine classifier when compared to the classical Support Vector Machine (SVM) classifier, especially in scenarios with less sample size and feature vector size. Surprisingly, our outcomes reveal that the quantum kernel strategy outperforms its traditional counterpart, even with a smaller sample-based dataset. This incredible performance can be attributed to the quantum core strategy’s exceptional ability to extract complex attributes, which enables it to extract more relevant insights from a smaller number of data points. We present a Quantum Kernel Support Vector Machine (QKSVM) built as a Quantum Kernel Circuit (QKC) in three configurations with varied qubit counts utilizing distinct embedding techniques: Angle embedding (QKSVM Angle), Instantaneous Quantum Polynomial embedding (QKSVM IQP), and Quantum Approximation Optimization Algorithm (QKSVM QAOA) embedding. Our results demonstrate that the QKSVM approach surpasses traditional SVM, especially when IQP embedding is employed. The QSVM model trained with four Principal Component Analysis (PCA) based selected relevant features outperforms the other QKC variations in cyclone classification, obtaining an excellent test accuracy rate of 91.66%.The paradigm of classical machine learning has been greatly revolutionized by the integration of the quantum computing paradigm, which has made it possible to solve complicated issues that were previously unsolvable by conventional computers. One such problem is accurately classifying cyclones with minimal data samples and feature parameters. In this paper, we investigate the superior learning capabilities of the Instantaneous Quantum Polynomial Embedding-based kernel Support Vector Machine classifier when compared to the classical Support Vector Machine (SVM) classifier, especially in scenarios with less sample size and feature vector size. Surprisingly, our outcomes reveal that the quantum kernel strategy outperforms its traditional counterpart, even with a smaller sample-based dataset. This incredible performance can be attributed to the quantum core strategy’s exceptional ability to extract complex attributes, which enables it to extract more relevant insights from a smaller number of data points. We present a Quantum Kernel Support Vector Machine (QKSVM) built as a Quantum Kernel Circuit (QKC) in three configurations with varied qubit counts utilizing distinct embedding techniques: Angle embedding (QKSVM Angle), Instantaneous Quantum Polynomial embedding (QKSVM IQP), and Quantum Approximation Optimization Algorithm (QKSVM QAOA) embedding. Our results demonstrate that the QKSVM approach surpasses traditional SVM, especially when IQP embedding is employed. The QSVM model trained with four Principal Component Analysis (PCA) based selected relevant features outperforms the other QKC variations in cyclone classification, obtaining an excellent test accuracy rate of 91.66%.

International Conference on Recent Trends in Advance Computing (ICRTAC)Dec 14, 20239 citations

(O(n^2))

(O(nm))

, while preserving the quantum advantages in handling high-dimensional, non-linear data. Extensive simulations demonstrate that NQ-SVM achieves comparable classification accuracy to classical SVMs and full QSVMs, while substantially reducing training time and kernel evaluation costs. These results underscore the potential of NQ-SVM as a scalable and practical hybrid framework for near-term quantum machine learning (QML).