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:2203.00031 · Quantum

The complexity of quantum support vector machines

Gian Gentinetta, Arne Thomsen, David Sutter, Stefan Woerner

Published Jan 11, 2024• 101 citations
arXivHTMLPDF

Abstract

Quantum support vector machines employ quantum circuits to define the kernel function. It has been shown that this approach offers a provable exponential speedup compared to any known classical algorithm for certain data sets. The training of such models corresponds to solving a convex optimization problem either via its primal or dual formulation. Due to the probabilistic nature of quantum mechanics, the training algorithms are affected by statistical uncertainty, which has a major impact on their complexity. We show that the dual problem can be solved in O ( M 4.67 / ε 2 ) quantum circuit evaluations, where M denotes the size of the data set and ε the solution accuracy compared to the ideal result from exact expectation values, which is only obtainable in theory. We prove under an empirically motivated assumption that the kernelized primal problem can alternatively be solved in O ( min { M 2 / ε 6 , 1 / ε 10 } ) evaluations by employing a generalization of a known classical algorithm called Pegasos. Accompanying empirical results demonstrate these analytical complexities to be essentially tight. In addition, we investigate a variational approximation to quantum support vector machines and show that their heuristic training achieves considerably better scaling in our experiments.

DOI
10.22331/q-2024-01-11-1225

Related papers

A Triple-Hybrid Quantum Support Vector Machine Using Classical, Quantum Gate-based and Quantum Annealing-based Computing

Juan C. Boschero, Ward van der Schoot, Niels M. P. Neumann

Quantum machine learning is one of the fields where quantum computers are expected to bring advantages over classical methods. However, the limited size of current computers restricts the exploitation of the full potential of quantum machine learning methods. Additionally, different computing paradigms, both quantum and classical, each have their own strengths and weaknesses. Obtaining optimal results with algorithms thus requires algorithms to be tweaked to the underlying computational paradigm, and the tasks to be optimally distributed over the available computational resources. In this work, we explore the potential gains from combining different computing paradigms to solve the complex task of data classification for three different datasets. We use a gate-based quantum model to implement a quantum kernel and implement a complex feature map. Next, we formulate a quadratic unconstrained optimisation problem to be solved on quantum annealing hardware. We then evaluate the losses on classical hardware and reconfigure the model parameters accordingly. We tested this so-called triple-hybrid quantum support vector machine on various data sets, and find that it achieves higher precision than other support vector machines (both quantum and classical) on complex quantum data, whereas it achieves varying performance on simple classical data using limited training. For the complex data sets, the triple-hybrid version converges faster, requiring fewer circuit evaluations.

quant-pharXiv:2511.05237•Nov 10, 2025•1 citation

Quantum Kernel Alignment with Stochastic Gradient Descent

Gian Gentinetta, David Sutter, Christa Zoufal +2 more

Quantum support vector machines have the potential to achieve a quantum speedup for solving certain machine learning problems. The key challenge for doing so is finding good quantum kernels for a given data set - a task called kernel alignment. In this paper we study this problem using the Pegasos algorithm, which is an algorithm that uses stochastic gradient descent to solve the support vector machine optimization problem. We extend Pegasos to the quantum case and and demonstrate its effectiveness for kernel alignment. Unlike previous work which performs kernel alignment by training a QSVM within an outer optimization loop, we show that using Pegasos it is possible to simultaneously train the support vector machine and align the kernel. Our experiments show that this approach is capable of aligning quantum feature maps with high accuracy, and outperforms existing quantum kernel alignment techniques. Specifically, we demonstrate that Pegasos is particularly effective for non-stationary data, which is an important challenge in real-world applications.

arXiv:2304.09899•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 17, 2023•22 citations

Implementation of Quantum Support Vector Machine Algorithm Using a Benchmarking Dataset

The evolution of quantum computers and quantum machine learning (QML) algorithms have started demonstrating exponential speed-ups. In machine learning problems, the efficient handling and manipulation of linear algebra subroutines defines the complexity of the task to be performed. Quantum computers handle big datasets in the form of vectors and matrix operations very efficiently. In this paper, quantum support vector machine (QSVM) algorithm is used to solve a classification problem using a benchmarking MNIST dataset of handwritten images of digits. Quantum SVM variational and kernel matrix algorithms are implemented to analyze quantum speedup on quantum simulator and physical quantum processor back-ends. The study compared classical and quantum SVM algorithms in terms of execution time and accuracy. The results explicitly prove quantum speed-up achieved by quantum classifiers on quantum back-ends for machine learning applications.

Indian Journal of Pure & Applied Physics•Apr 28, 2022•23 citations

Quantum Support Vector Machine for Big Data Classification

Patrick Rebentrost, Masoud Mohseni, Seth Lloyd

Supervised machine learning is the classification of new data based on already classified training examples. In this work, we show that the support vector machine, an optimized binary classifier, can be implemented on a quantum computer, with complexity logarithmic in the size of the vectors and the number of training examples. In cases where classical sampling algorithms require polynomial time, an exponential speedup is obtained. At the core of this quantum big data algorithm is a nonsparse matrix exponentiation technique for efficiently performing a matrix inversion of the training data inner-product (kernel) matrix.

arXiv:1307.0471•Physical Review Letters•Sep 25, 2014•2,147 citations

Support Vector Machine with a Scalable Quantum Kernel

Anant Agnihotri, Michael Krebsbach, Florentin Reiter +1 more

Quantum support vector machines are classification algorithms that rely on quantum-generated kernels. The fidelity quantum kernel commonly used in quantum support vector machines suffers from exponential concentration as system size increases, preventing an efficient scaling beyond fewqubit systems. We introduce the Hamming quantum kernel, a classical post-processing method that is based on the same measurement outcomes as the fidelity quantum kernel. However, it avoids the exponential concentration problem by using the full measurement statistics rather than a single fidelity value. We evaluate the approach on both classical data (MNIST) and synthetic data generated from quantum circuits, using systems ranging from 2 to 27 qubits. Throughout the simulations, the Hamming quantum kernel outperforms the fidelity quantum kernel whenever 15 or more qubits are used. Furthermore, for synthetic quantum data, our method consistently outperforms the classical Gaussian kernel. This demonstrates that the Hamming quantum kernel improves the expressivity and robustness at larger qubit scales without requiring any additional quantum ressources.

quant-pharXiv:2605.31449•Jun 1, 2026•1 citation

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).

•Mar 3, 2026•0 citations
Quantum support vector machines employ quantum circuits to define the kernel function. It has been shown that this approach offers a provable exponential speedup compared to any known classical algorithm for certain data sets. The training of such models corresponds to solving a convex optimization problem either via its primal or dual formulation. Due to the probabilistic nature of quantum mechanics, the training algorithms are affected by statistical uncertainty, which has a major impact on their complexity. We show that the dual problem can be solved in O ( M 4.67 / ε 2 ) quantum circuit evaluations, where M denotes the size of the data set and ε the solution accuracy compared to the ideal result from exact expectation values, which is only obtainable in theory. We prove under an empirically motivated assumption that the kernelized primal problem can alternatively be solved in O ( min { M 2 / ε 6 , 1 / ε 10 } ) evaluations by employing a generalization of a known classical algorithm called Pegasos. Accompanying empirical results demonstrate these analytical complexities to be essentially tight. In addition, we investigate a variational approximation to quantum support vector machines and show that their heuristic training achieves considerably better scaling in our experiments.
Quantum machine learning is one of the fields where quantum computers are expected to bring advantages over classical methods. However, the limited size of current computers restricts the exploitation of the full potential of quantum machine learning methods. Additionally, different computing paradigms, both quantum and classical, each have their own strengths and weaknesses. Obtaining optimal results with algorithms thus requires algorithms to be tweaked to the underlying computational paradigm, and the tasks to be optimally distributed over the available computational resources. In this work, we explore the potential gains from combining different computing paradigms to solve the complex task of data classification for three different datasets. We use a gate-based quantum model to implement a quantum kernel and implement a complex feature map. Next, we formulate a quadratic unconstrained optimisation problem to be solved on quantum annealing hardware. We then evaluate the losses on classical hardware and reconfigure the model parameters accordingly. We tested this so-called triple-hybrid quantum support vector machine on various data sets, and find that it achieves higher precision than other support vector machines (both quantum and classical) on complex quantum data, whereas it achieves varying performance on simple classical data using limited training. For the complex data sets, the triple-hybrid version converges faster, requiring fewer circuit evaluations.
Quantum support vector machines have the potential to achieve a quantum speedup for solving certain machine learning problems. The key challenge for doing so is finding good quantum kernels for a given data set - a task called kernel alignment. In this paper we study this problem using the Pegasos algorithm, which is an algorithm that uses stochastic gradient descent to solve the support vector machine optimization problem. We extend Pegasos to the quantum case and and demonstrate its effectiveness for kernel alignment. Unlike previous work which performs kernel alignment by training a QSVM within an outer optimization loop, we show that using Pegasos it is possible to simultaneously train the support vector machine and align the kernel. Our experiments show that this approach is capable of aligning quantum feature maps with high accuracy, and outperforms existing quantum kernel alignment techniques. Specifically, we demonstrate that Pegasos is particularly effective for non-stationary data, which is an important challenge in real-world applications.
The evolution of quantum computers and quantum machine learning (QML) algorithms have started demonstrating exponential speed-ups. In machine learning problems, the efficient handling and manipulation of linear algebra subroutines defines the complexity of the task to be performed. Quantum computers handle big datasets in the form of vectors and matrix operations very efficiently. In this paper, quantum support vector machine (QSVM) algorithm is used to solve a classification problem using a benchmarking MNIST dataset of handwritten images of digits. Quantum SVM variational and kernel matrix algorithms are implemented to analyze quantum speedup on quantum simulator and physical quantum processor back-ends. The study compared classical and quantum SVM algorithms in terms of execution time and accuracy. The results explicitly prove quantum speed-up achieved by quantum classifiers on quantum back-ends for machine learning applications.
Supervised machine learning is the classification of new data based on already classified training examples. In this work, we show that the support vector machine, an optimized binary classifier, can be implemented on a quantum computer, with complexity logarithmic in the size of the vectors and the number of training examples. In cases where classical sampling algorithms require polynomial time, an exponential speedup is obtained. At the core of this quantum big data algorithm is a nonsparse matrix exponentiation technique for efficiently performing a matrix inversion of the training data inner-product (kernel) matrix.
Quantum support vector machines are classification algorithms that rely on quantum-generated kernels. The fidelity quantum kernel commonly used in quantum support vector machines suffers from exponential concentration as system size increases, preventing an efficient scaling beyond fewqubit systems. We introduce the Hamming quantum kernel, a classical post-processing method that is based on the same measurement outcomes as the fidelity quantum kernel. However, it avoids the exponential concentration problem by using the full measurement statistics rather than a single fidelity value. We evaluate the approach on both classical data (MNIST) and synthetic data generated from quantum circuits, using systems ranging from 2 to 27 qubits. Throughout the simulations, the Hamming quantum kernel outperforms the fidelity quantum kernel whenever 15 or more qubits are used. Furthermore, for synthetic quantum data, our method consistently outperforms the classical Gaussian kernel. This demonstrates that the Hamming quantum kernel improves the expressivity and robustness at larger qubit scales without requiring any additional quantum ressources.
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(n2))(O(n^2))(O(n2)) to (O(nm))(O(nm))(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).