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:2610.39350

Provably efficient experimental classification of quantum data with quantum kernels

Keitaro Anai, Akimoto Nakayama, Shintaro Ooka, Hiroko Tomoda, Yuto Morohoshi, Yohji Chin, Shigehito Miki, Masahiro Yabuno, Hirotaka Terai, Peter van Loock, Kosuke Mitarai, Shuntaro Takeda

quant-phSubmitted Oct 29, 2026• Announced Oct 30, 2026• 0 citations
arXivHTMLPDF

Abstract

Analyzing quantum systems is essential for quantum information processing, but can require exponentially many measurements without exploiting the structure of the system or task. Quantum machine learning offers a promising way to reduce this cost by learning from quantum data. Here, we theoretically establish a framework for efficient quantum-state classification and experimentally demonstrate the resulting scheme on a programmable photonic processor. Our analysis links learning efficiency to the structure of quantum data, without relying on a physical description tailored to each task. We derive sufficient conditions for accurate classification with a number of measurements polynomial in system size. We apply this guarantee to a resource problem in continuous-variable (CV) quantum computing: classifying stellar rank, a measure of non-Gaussianity. Experimentally, we implement the classification of single-mode CV quantum states with stellar rank zero and one. This is enabled by developing a programmable CV photonic processor capable of preparing and processing diverse Gaussian and non-Gaussian states and performing virtual projection onto such states, going beyond the Gaussian-only capabilities of most existing photonic platforms. The experiment demonstrates accurate classification despite experimental imperfections. Our results establish a theory-guided and experimentally validated framework for quantum-state classification that can be implemented on quantum devices available today.

AI Summary

The paper asks when fidelity-based quantum kernels can classify quantum states with polynomial measurement resources, rather than reconstructing them tomographically. It analyzes a support-vector machine using the RBF kernel $K(\psi,\phi)=\exp[-(1-|\langle\psi|\phi\rangle|^2)/\sigma^2]$ and demonstrates binary stellar-rank classification on a programmable continuous-variable photonic processor. The guarantee assumes one class has $M$ representative states: every same-class state has kernel similarity at least $\kappa$ to some representative, while opposite-class similarities are at most $\varepsilon_{\mathrm{sep}}$. An inverse-polynomial positive margin $\eta=\kappa/M-\varepsilon_{\mathrm{sep}}$, together with a noncollapse condition, suffices for polynomial-resource learning. The proof constructs an RKHS separator and combines generalization bounds with finite-shot kernel estimation and positive-semidefinite projection. For target error $\epsilon$, sufficient training-set size is $\widetilde O(\eta^{-2}\epsilon^{-2})$; training and per-prediction measurement counts are $\widetilde O(\sigma^{-4}\eta^{-12}\epsilon^{-12})$ and $\widetilde O(\sigma^{-4}\eta^{-6}\epsilon^{-4})$. Stellar-rank-zero/one simulations cover one to three modes, using datasets constructed around $9m(m+1)$ representatives per class with within-representative fidelity at least $0.9$. The experiment measures kernels for 180 single-mode Gaussian-transformed vacuum and single-photon states. RBF classification accuracy approaches unity with increasing training size despite imperfections. The stated guarantees concern ideal state families and sufficient theoretical bandwidth choices, not the cross-validated bandwidths used in practice. The experimental homodyne estimator also differs from the bounded-outcome model analyzed theoretically. The demonstrations involve small, simple states and establish no quantum advantage; baseline comparisons do not compare measurement-shot costs.

Little sign of AI-generated textStrong assumptionsIncremental

Error found: The experiment demonstrates classification accuracy, but its homodyne estimator, noisy kernels, and cross-validated kernel width are not covered by the paper's polynomial-measurement guarantee, a limitation explicitly acknowledged in the supplement.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
9 pages, 5 figures for the main text, and 22 pages and 6 figures for the supplementary information

Related papers

Continuous-variable quantum kernel method on a programmable photonic quantum processor

Keitaro Anai, Shion Ikehara, Yoshichika Yano +2 more

Among various quantum machine learning (QML) algorithms, the quantum kernel method has especially attracted attention due to its compatibility with noisy intermediate-scale quantum devices and its potential to achieve quantum advantage. This method performs classification and regression by nonlinearly mapping data into quantum states in a higher-dimensional Hilbert space. Thus far, the quantum kernel method has been implemented only on qubit-based systems, but continuous-variable (CV) systems can potentially offer superior computational power by utilizing its infinite-dimensional Hilbert space. Here, we demonstrate the implementation of the classification task with the CV quantum kernel method on a programmable photonic quantum processor. We experimentally prove that the CV quantum kernel method successfully classifies several datasets robustly even under the experimental imperfections, with high accuracies comparable to the classical kernel. This demonstration sheds light on the utility of CV quantum systems for QML and should stimulate further study in other CV QML algorithms.

arXiv:2405.01086•Physical Review A•Aug 2, 2024•10 citations

Quantum Kernel Machine Learning With Continuous Variables

Laura J. Henderson, Rishi Goel, Sally Shrapnel

The popular qubit framework has dominated recent work on quantum kernel machine learning, with results characterising expressivity, learnability and generalisation. As yet, there is no comparative framework to understand these concepts for continuous variable (CV) quantum computing platforms. In this paper we represent CV quantum kernels as closed form functions and use this representation to provide several important theoretical insights. We derive a general closed form solution for all CV quantum kernels and show every such kernel can be expressed as the product of a Gaussian and an algebraic function of the parameters of the feature map. Furthermore, in the multi-mode case, we present quantification of a quantum-classical separation for all quantum kernels via a hierarchical notion of the “stellar rank" of the quantum kernel feature map. We then prove kernels defined by feature maps of infinite stellar rank, such as GKP-state encodings, can be approximated arbitrarily well by kernels defined by feature maps of finite stellar rank. Finally, we simulate learning with a single-mode displaced Fock state encoding and show that (i) accuracy on our specific task (an annular data set) increases with stellar rank, (ii) for underfit models, accuracy can be improved by increasing a bandwidth hyperparameter, and (iii) for noisy data that is overfit, decreasing the bandwidth will improve generalisation but does so at the cost of effective stellar rank.

arXiv:2401.05647•Quantum•Dec 17, 2024•11 citations

Demonstration of continuous-variable quantum machine learning using optical circuits

Shion Ikehara, Keitaro Anai, Yoshichika Yano +2 more

We demonstrate the implementation of the classification task with the continuous-variable (CV) quantum kernel method on a programmable photonic quantum processor. We experimentally prove that the CV quantum kernel method successfully classifies several datasets robustly.

Frontiers in Optics•Jan 1, 2024•0 citations

Experimental data reuploading with provable enhanced learning capabilities

Martin F. X. Mauser, Solène Four, Lena Marie Predl +7 more

The past decades have seen the development of quantum machine learning, stemming from the intersection of quantum computing and machine learning. This field is particularly promising for the design of alternative quantum (or quantum inspired) computation paradigms that could require fewer resources with respect to standard ones, e.g., in terms of energy consumption. In this context, we present the implementation of a data reuploading scheme on a photonic integrated processor, achieving high accuracies in several image classification tasks. We thoroughly investigate the capabilities of this apparently simple model, which relies on the evolution of one-qubit states, by providing an analytical proof that our implementation is a universal classifier and an effective learner, capable of generalizing to new, unknown data. Hence, our results not only demonstrate data reuploading in a potentially resource-efficient optical implementation but also provide theoretical insight into this algorithm, its trainability, and generalizability properties. This lays the groundwork for developing more resource-efficient machine learning algorithms, leveraging our scheme as a subroutine.

arXiv:2507.05120•Science Advances•Apr 10, 2026•4 citations

Hardware-inspired Continuous Variables Quantum Optical Neural Networks

Todor Krasimirov-Ivanov, Alba Cervera-Lierta, Paolo Stornati +1 more

Continuous-variables (CV) quantum optics is a natural formalism for neural networks (NNs) due to its ability to reproduce the information processing of such trainable interconnected systems. In quantum optics, Gaussian operators induce affine mappings on the quadratures of optical modes while non-Gaussian resources (the challenging piece for physical implementation) originate the nonlinear effects, unlocking quantum analogs of an artificial neuron. This work presents a novel experimentally-feasible framework for continuous-variable quantum optical neural networks (QONNs) developed with available photonic components: coherent states as input encoding, a general Gaussian transformation followed by multi-mode photon subtractions as the processing layer, and homodyne detection as outputs readout. The closed-form expressions of such architecture are derived demonstrating the family of adaptive activations and the quantum-optical neurons that emerge from the amount of photon-subtracted modes, proving that the proposed design satisfies the Universal Approximation Theorem within a single layer. To classically simulate the QONN training, the high-performance QuaNNTO library has been developed based on Wick-Isserlis expansion and Bogoliubov transformations, allowing multi-layer exact expectation values of non-Gaussian states without truncating the infinite-dimensional Hilbert space. Experiments on supervised learning and state-preparation tasks show balanced-resource efficiency with strong expressivity and generalization capabilities, illustrating the potential of the architecture for scalable photonic quantum machine learning and for quantum applications such as complex non-Gaussian gate synthesis.

quant-pharXiv:2512.05204•Dec 8, 2025•1 citation

A Resource Efficient Quantum Kernel

Utkarsh Singh, Jean‐Frédéric Laprade, Aaron Z. Goldberg +1 more

Quantum processors may enhance machine learning by mapping high-dimensional data onto quantum systems for processing. Conventional feature maps, for encoding data onto a quantum circuit are currently impractical, as the number of entangling gates scales quadratically with the dimension of the dataset and the number of qubits. In this work, we introduce a quantum feature map designed to handle high-dimensional data with a significantly reduced number of qubits and entangling operations. Our approach preserves essential data characteristics while promoting computational efficiency, as evidenced by extensive experiments on benchmark datasets that demonstrate a marked improvement in both accuracy and resource utilization when using our feature map as a kernel for characterization, as compared to state-of-the-art quantum feature maps. Our noisy simulation results, combined with lower resource requirements, highlight our map's ability to function within the constraints of noisy intermediate-scale quantum devices. Through numerical simulations and small-scale implementation on a superconducting circuit quantum computing platform, we demonstrate that our scheme performs on par or better than a set of classical algorithms for classification. While quantum kernels are typically stymied by exponential concentration, our approach is affected with a slower rate with respect to both the number of qubits and features, which allows practical applications to remain within reach. Our findings herald a promising avenue for the practical implementation of quantum machine learning algorithms on near future quantum computing platforms.

arXiv:2507.03689•Jul 4, 2025•7 citations
Analyzing quantum systems is essential for quantum information processing, but can require exponentially many measurements without exploiting the structure of the system or task. Quantum machine learning offers a promising way to reduce this cost by learning from quantum data. Here, we theoretically establish a framework for efficient quantum-state classification and experimentally demonstrate the resulting scheme on a programmable photonic processor. Our analysis links learning efficiency to the structure of quantum data, without relying on a physical description tailored to each task. We derive sufficient conditions for accurate classification with a number of measurements polynomial in system size. We apply this guarantee to a resource problem in continuous-variable (CV) quantum computing: classifying stellar rank, a measure of non-Gaussianity. Experimentally, we implement the classification of single-mode CV quantum states with stellar rank zero and one. This is enabled by developing a programmable CV photonic processor capable of preparing and processing diverse Gaussian and non-Gaussian states and performing virtual projection onto such states, going beyond the Gaussian-only capabilities of most existing photonic platforms. The experiment demonstrates accurate classification despite experimental imperfections. Our results establish a theory-guided and experimentally validated framework for quantum-state classification that can be implemented on quantum devices available today.
The paper asks when fidelity-based quantum kernels can classify quantum states with polynomial measurement resources, rather than reconstructing them tomographically. It analyzes a support-vector machine using the RBF kernel K(ψ,ϕ)=exp⁡[−(1−∣⟨ψ∣ϕ⟩∣2)/σ2]K(\psi,\phi)=\exp[-(1-|\langle\psi|\phi\rangle|^2)/\sigma^2]K(ψ,ϕ)=exp[−(1−∣⟨ψ∣ϕ⟩∣2)/σ2] and demonstrates binary stellar-rank classification on a programmable continuous-variable photonic processor.
The guarantee assumes one class has MMM representative states: every same-class state has kernel similarity at least κ\kappaκ to some representative, while opposite-class similarities are at most εsep\varepsilon_{\mathrm{sep}}εsep​. An inverse-polynomial positive margin η=κ/M−εsep\eta=\kappa/M-\varepsilon_{\mathrm{sep}}η=κ/M−εsep​, together with a noncollapse condition, suffices for polynomial-resource learning. The proof constructs an RKHS separator and combines generalization bounds with finite-shot kernel estimation and positive-semidefinite projection. For target error ϵ\epsilonϵ, sufficient training-set size is O~(η−2ϵ−2)\widetilde O(\eta^{-2}\epsilon^{-2})O(η−2ϵ−2); training and per-prediction measurement counts are O~(σ−4η−12ϵ−12)\widetilde O(\sigma^{-4}\eta^{-12}\epsilon^{-12})O(σ−4η−12ϵ−12) and O~(σ−4η−6ϵ−4)\widetilde O(\sigma^{-4}\eta^{-6}\epsilon^{-4})O(σ−4η−6ϵ−4).
Stellar-rank-zero/one simulations cover one to three modes, using datasets constructed around 9m(m+1)9m(m+1)9m(m+1) representatives per class with within-representative fidelity at least 0.90.90.9. The experiment measures kernels for 180 single-mode Gaussian-transformed vacuum and single-photon states. RBF classification accuracy approaches unity with increasing training size despite imperfections.
The stated guarantees concern ideal state families and sufficient theoretical bandwidth choices, not the cross-validated bandwidths used in practice. The experimental homodyne estimator also differs from the bounded-outcome model analyzed theoretically. The demonstrations involve small, simple states and establish no quantum advantage; baseline comparisons do not compare measurement-shot costs.
Among various quantum machine learning (QML) algorithms, the quantum kernel method has especially attracted attention due to its compatibility with noisy intermediate-scale quantum devices and its potential to achieve quantum advantage. This method performs classification and regression by nonlinearly mapping data into quantum states in a higher-dimensional Hilbert space. Thus far, the quantum kernel method has been implemented only on qubit-based systems, but continuous-variable (CV) systems can potentially offer superior computational power by utilizing its infinite-dimensional Hilbert space. Here, we demonstrate the implementation of the classification task with the CV quantum kernel method on a programmable photonic quantum processor. We experimentally prove that the CV quantum kernel method successfully classifies several datasets robustly even under the experimental imperfections, with high accuracies comparable to the classical kernel. This demonstration sheds light on the utility of CV quantum systems for QML and should stimulate further study in other CV QML algorithms.
The popular qubit framework has dominated recent work on quantum kernel machine learning, with results characterising expressivity, learnability and generalisation. As yet, there is no comparative framework to understand these concepts for continuous variable (CV) quantum computing platforms. In this paper we represent CV quantum kernels as closed form functions and use this representation to provide several important theoretical insights. We derive a general closed form solution for all CV quantum kernels and show every such kernel can be expressed as the product of a Gaussian and an algebraic function of the parameters of the feature map. Furthermore, in the multi-mode case, we present quantification of a quantum-classical separation for all quantum kernels via a hierarchical notion of the “stellar rank" of the quantum kernel feature map. We then prove kernels defined by feature maps of infinite stellar rank, such as GKP-state encodings, can be approximated arbitrarily well by kernels defined by feature maps of finite stellar rank. Finally, we simulate learning with a single-mode displaced Fock state encoding and show that (i) accuracy on our specific task (an annular data set) increases with stellar rank, (ii) for underfit models, accuracy can be improved by increasing a bandwidth hyperparameter, and (iii) for noisy data that is overfit, decreasing the bandwidth will improve generalisation but does so at the cost of effective stellar rank.
The past decades have seen the development of quantum machine learning, stemming from the intersection of quantum computing and machine learning. This field is particularly promising for the design of alternative quantum (or quantum inspired) computation paradigms that could require fewer resources with respect to standard ones, e.g., in terms of energy consumption. In this context, we present the implementation of a data reuploading scheme on a photonic integrated processor, achieving high accuracies in several image classification tasks. We thoroughly investigate the capabilities of this apparently simple model, which relies on the evolution of one-qubit states, by providing an analytical proof that our implementation is a universal classifier and an effective learner, capable of generalizing to new, unknown data. Hence, our results not only demonstrate data reuploading in a potentially resource-efficient optical implementation but also provide theoretical insight into this algorithm, its trainability, and generalizability properties. This lays the groundwork for developing more resource-efficient machine learning algorithms, leveraging our scheme as a subroutine.
Continuous-variables (CV) quantum optics is a natural formalism for neural networks (NNs) due to its ability to reproduce the information processing of such trainable interconnected systems. In quantum optics, Gaussian operators induce affine mappings on the quadratures of optical modes while non-Gaussian resources (the challenging piece for physical implementation) originate the nonlinear effects, unlocking quantum analogs of an artificial neuron. This work presents a novel experimentally-feasible framework for continuous-variable quantum optical neural networks (QONNs) developed with available photonic components: coherent states as input encoding, a general Gaussian transformation followed by multi-mode photon subtractions as the processing layer, and homodyne detection as outputs readout. The closed-form expressions of such architecture are derived demonstrating the family of adaptive activations and the quantum-optical neurons that emerge from the amount of photon-subtracted modes, proving that the proposed design satisfies the Universal Approximation Theorem within a single layer. To classically simulate the QONN training, the high-performance QuaNNTO library has been developed based on Wick-Isserlis expansion and Bogoliubov transformations, allowing multi-layer exact expectation values of non-Gaussian states without truncating the infinite-dimensional Hilbert space. Experiments on supervised learning and state-preparation tasks show balanced-resource efficiency with strong expressivity and generalization capabilities, illustrating the potential of the architecture for scalable photonic quantum machine learning and for quantum applications such as complex non-Gaussian gate synthesis.
Quantum processors may enhance machine learning by mapping high-dimensional data onto quantum systems for processing. Conventional feature maps, for encoding data onto a quantum circuit are currently impractical, as the number of entangling gates scales quadratically with the dimension of the dataset and the number of qubits. In this work, we introduce a quantum feature map designed to handle high-dimensional data with a significantly reduced number of qubits and entangling operations. Our approach preserves essential data characteristics while promoting computational efficiency, as evidenced by extensive experiments on benchmark datasets that demonstrate a marked improvement in both accuracy and resource utilization when using our feature map as a kernel for characterization, as compared to state-of-the-art quantum feature maps. Our noisy simulation results, combined with lower resource requirements, highlight our map's ability to function within the constraints of noisy intermediate-scale quantum devices. Through numerical simulations and small-scale implementation on a superconducting circuit quantum computing platform, we demonstrate that our scheme performs on par or better than a set of classical algorithms for classification. While quantum kernels are typically stymied by exponential concentration, our approach is affected with a slower rate with respect to both the number of qubits and features, which allows practical applications to remain within reach. Our findings herald a promising avenue for the practical implementation of quantum machine learning algorithms on near future quantum computing platforms.