For quantum classification methods, the quantum kernel has a role in encoding the data set from its original low-dimensional real space into a high-dimensional quantum state space utilizing quantum circuits. Finding quantum kernels that provide an advantage in real-world data classification is a major challenge, especially when dealing with heterogeneous data or a large data set, requiring more qubits than are available on current devices. Here, we propose two new methods: first, we implement a multiple kernel method for data coming from multiple sources, and second, we propose to combine quantum chips to process larger data sets. The latter can be realized by splitting larger quantum circuits into smaller sub-circuits. We experimentally implement a multiple quantum kernel approach for different data sets on IBM quantum computers and benchmark their results.For quantum classification methods, the quantum kernel has a role in encoding the data set from its original low-dimensional real space into a high-dimensional quantum state space utilizing quantum circuits. Finding quantum kernels that provide an advantage in real-world data classification is a major challenge, especially when dealing with heterogeneous data or a large data set, requiring more qubits than are available on current devices. Here, we propose two new methods: first, we implement a multiple kernel method for data coming from multiple sources, and second, we propose to combine quantum chips to process larger data sets. The latter can be realized by splitting larger quantum circuits into smaller sub-circuits. We experimentally implement a multiple quantum kernel approach for different data sets on IBM quantum computers and benchmark their results.

International Conference on Information Fusion (FUSION)Jul 4, 20220 citations

Quantum Machine Learning Models for High-Dimensional Data Analysis

Ambuj Kumar Agarwal, Pradnya Sulas Borkar, Sumit Chafle +3 more

International Conference on Emerging Smart Computing and Informatics (ESCI)Mar 11, 20260 citations

Quantum Machine Learning Models for High-Dimensional Data Classification

Ivan Bianchi, Clara Costa, Jonas Dubois

High-dimensional data classification -- where feature dimensionality p exceeds or approaches sample size n -- is ubiquitous in genomics, medical imaging, spectroscopy, and financial risk modelling. Quantum machine learning (QML) offers potential advantages for high-dimensional classification through quantum feature maps that implicitly operate in exponentially large Hilbert spaces, potentially capturing feature correlations inaccessible to polynomial-complexity classical kernel methods. However, identifying when and why QML provides genuine classification advantage over classical methods for high-dimensional data remains an open question, complicated by the QCCB finding (Popescu and Petrov, 2024) that quantum kernel advantages are dataset-specific. This paper proposes the Quantum High-Dimensional Classification (QHDC) framework, investigating QML advantage for five high-dimensional classification problems across three quantum model families: quantum kernel SVM (QKSVM) using parameterised ZZFeatureMap and IQPFeatureMap; quantum neural network classifier (QNNC) using LSAD-structured ansatz (Silva et al., 2024); and quantum-classical transfer learning (QCTL) using a quantum feature extractor with classical fine-tuning head. QHDC is evaluated on five datasets: genomic variant classification (p=8,442, n=284), hyperspectral remote sensing (p=200, n=10,249), drug-protein binding prediction (p=1,024, n=4,284), financial credit risk (p=84, n=28,400), and quantum chemistry energy prediction (p=48, n=2,840). QKSVM achieves the highest QML performance: AUC improvement over classical RBF-SVM of 2.4-8.4pp across five datasets, with largest gains on quantum chemistry (8.4pp) and drug- protein (6.4pp) datasets. QNNC underperforms classical baselines on three of five datasets due to barren plateau limitations at high dimensionality. QCTL achieves 4.4pp improvement on genomic classification.High-dimensional data classification -- where feature dimensionality p exceeds or approaches sample size n -- is ubiquitous in genomics, medical imaging, spectroscopy, and financial risk modelling. Quantum machine learning (QML) offers potential advantages for high-dimensional classification through quantum feature maps that implicitly operate in exponentially large Hilbert spaces, potentially capturing feature correlations inaccessible to polynomial-complexity classical kernel methods. However, identifying when and why QML provides genuine classification advantage over classical methods for high-dimensional data remains an open question, complicated by the QCCB finding (Popescu and Petrov, 2024) that quantum kernel advantages are dataset-specific. This paper proposes the Quantum High-Dimensional Classification (QHDC) framework, investigating QML advantage for five high-dimensional classification problems across three quantum model families: quantum kernel SVM (QKSVM) using parameterised ZZFeatureMap and IQPFeatureMap; quantum neural network classifier (QNNC) using LSAD-structured ansatz (Silva et al., 2024); and quantum-classical transfer learning (QCTL) using a quantum feature extractor with classical fine-tuning head. QHDC is evaluated on five datasets: genomic variant classification (p=8,442, n=284), hyperspectral remote sensing (p=200, n=10,249), drug-protein binding prediction (p=1,024, n=4,284), financial credit risk (p=84, n=28,400), and quantum chemistry energy prediction (p=48, n=2,840). QKSVM achieves the highest QML performance: AUC improvement over classical RBF-SVM of 2.4-8.4pp across five datasets, with largest gains on quantum chemistry (8.4pp) and drug- protein (6.4pp) datasets. QNNC underperforms classical baselines on three of five datasets due to barren plateau limitations at high dimensionality. QCTL achieves 4.4pp improvement on genomic classification.

Quantum Frontiers JournalMar 28, 20240 citations

Kernel methods in Quantum Machine Learning

Riccardo Mengoni, Alessandra Di Pierro

Quantum Machine IntelligenceNov 15, 201966 citations

A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification

Jiang Yuhan, Matthew Otten

Quantum kernel methods are a promising branch of quantum machine learning, but their per- formance across data types and encoding choices remains incompletely understood. To address this gap, we developed an algorithmic framework for variational quantum kernels utilizing resource- efficient ansätze for complex classification tasks and introduced a parameter scaling technique to accelerate convergence. We conducted a comprehensive benchmark of this framework on eight chal- lenging, real-world and high-dimensional datasets covering tabular, image, time series, and graph data. Our results show that the proposed quantum kernel demonstrated competitive classification accuracy compared to standard classical kernels in classical simulation, such as the radial basis function (RBF) kernel. This work demonstrates that properly designed quantum kernels can func- tion as versatile, high-performance tools, laying a foundation for quantum-enhanced applications in machine learning. Further research is needed to fully assess the practical performance of quantum methods.Quantum kernel methods are a promising branch of quantum machine learning, but their per- formance across data types and encoding choices remains incompletely understood. To address this gap, we developed an algorithmic framework for variational quantum kernels utilizing resource- efficient ansätze for complex classification tasks and introduced a parameter scaling technique to accelerate convergence. We conducted a comprehensive benchmark of this framework on eight chal- lenging, real-world and high-dimensional datasets covering tabular, image, time series, and graph data. Our results show that the proposed quantum kernel demonstrated competitive classification accuracy compared to standard classical kernels in classical simulation, such as the radial basis function (RBF) kernel. This work demonstrates that properly designed quantum kernels can func- tion as versatile, high-performance tools, laying a foundation for quantum-enhanced applications in machine learning. Further research is needed to fully assess the practical performance of quantum methods.

cs.LGCross-listedarXiv:2511.10831Nov 17, 20250 citations

Large-Scale Quantum Kernels for Hyperspectral Data Classification

Amer Delilbasic, Artur Miroszewski, Agata M. Wijata +4 more

Quantum kernel methods have emerged as a promising approach for leveraging high-dimensional feature spaces in machine learning, particularly in domains where classical kernel methods face scalability limitations. In this work, we present the first large-scale study of fidelity-quantum-kernel support vector machines for hyperspectral data classification without requiring heavy prior feature selection or dimensionality reduction. By simulating quantum kernels using tensor network contraction techniques and graphics processing unit acceleration, we overcome the computational bottlenecks traditionally associated with quantum models, achieving quadratic scaling $O(n^2)$ in the number of qubits. Our approach enables the evaluation of quantum kernels on hyperspectral data with hundreds of spectral bands, aligning quantum feature spaces with real-world remote sensing applications. We provide an in-depth analysis of kernel bandwidth optimization, demonstrating its crucial role in mitigating exponential concentration effects and ensuring the model's ability to generalize. Experimental results on binary classification (Indian Pines and methane detection) and multiclass classification (Indian Pines) demonstrate that quantum kernels achieve competitive performance compared to a broad range of state-of-the-art classical baselines. As illustrative cases, on four 50-band splits selected from Indian Pines, the quantum model achieved a $78.0±6.2\%$ accuracy for a binary classification task compared to $72.0±5.0\%$ for the standard radial basis function kernel. For a four-class classification task, the quantum kernel reached $83.3±3.1\%$ accuracy, outperforming several state-of-the-art baselines. On five 75-band splits selected from the methane detection dataset, the quantum approach yielded $58.5±5.0\%$ accuracy versus $55.1±2.5\%$ for the classical counterpart. This study provides a foundation for future exploration of quantum machine learning in high-dimensional Earth observation tasks.Quantum kernel methods have emerged as a promising approach for leveraging high-dimensional feature spaces in machine learning, particularly in domains where classical kernel methods face scalability limitations. In this work, we present the first large-scale study of fidelity-quantum-kernel support vector machines for hyperspectral data classification without requiring heavy prior feature selection or dimensionality reduction. By simulating quantum kernels using tensor network contraction techniques and graphics processing unit acceleration, we overcome the computational bottlenecks traditionally associated with quantum models, achieving quadratic scaling $O(n^2)$ in the number of qubits. Our approach enables the evaluation of quantum kernels on hyperspectral data with hundreds of spectral bands, aligning quantum feature spaces with real-world remote sensing applications. We provide an in-depth analysis of kernel bandwidth optimization, demonstrating its crucial role in mitigating exponential concentration effects and ensuring the model's ability to generalize. Experimental results on binary classification (Indian Pines and methane detection) and multiclass classification (Indian Pines) demonstrate that quantum kernels achieve competitive performance compared to a broad range of state-of-the-art classical baselines. As illustrative cases, on four 50-band splits selected from Indian Pines, the quantum model achieved a $78.0±6.2\%$ accuracy for a binary classification task compared to $72.0±5.0\%$ for the standard radial basis function kernel. For a four-class classification task, the quantum kernel reached $83.3±3.1\%$ accuracy, outperforming several state-of-the-art baselines. On five 75-band splits selected from the methane detection dataset, the quantum approach yielded $58.5±5.0\%$ accuracy versus $55.1±2.5\%$ for the classical counterpart. This study provides a foundation for future exploration of quantum machine learning in high-dimensional Earth observation tasks.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingJan 1, 20260 citations

O(n^2)

in the number of qubits. Our approach enables the evaluation of quantum kernels on hyperspectral data with hundreds of spectral bands, aligning quantum feature spaces with real-world remote sensing applications. We provide an in-depth analysis of kernel bandwidth optimization, demonstrating its crucial role in mitigating exponential concentration effects and ensuring the model's ability to generalize. Experimental results on binary classification (Indian Pines and methane detection) and multiclass classification (Indian Pines) demonstrate that quantum kernels achieve competitive performance compared to a broad range of state-of-the-art classical baselines. As illustrative cases, on four 50-band splits selected from Indian Pines, the quantum model achieved a

78.0±6.2\%

accuracy for a binary classification task compared to

72.0±5.0\%

for the standard radial basis function kernel. For a four-class classification task, the quantum kernel reached

83.3±3.1\%

accuracy, outperforming several state-of-the-art baselines. On five 75-band splits selected from the methane detection dataset, the quantum approach yielded

58.5±5.0\%

accuracy versus

55.1±2.5\%

for the classical counterpart. This study provides a foundation for future exploration of quantum machine learning in high-dimensional Earth observation tasks.