betaFeedback

WorksEngineering

Adaptive Low-Rank Quantum Kernel Acquisition under Finite-Shot Measurements: Perturbation Guarantees for QSVMs

Abstract

Quantum kernel methods require estimating entries of a dense Gram matrix through repeated circuit measurements, making kernel construction expensive and statistically noisy. For a dataset of size nn, dense construction requires O(n2)O(n^2) kernel queries, while existing approximation methods typically assume inexpensive access to kernel entries or use non-adaptive sampling. We study adaptive low-rank quantum kernel acquisition when the kernel is accessible only through a finite-shot quantum overlap oracle. Our framework, ICAQKL, uses residual-driven incomplete Cholesky construction to acquire informative kernel columns sequentially and form a positive-semidefinite rank-rr surrogate, reducing the training-kernel acquisition cost to O(nrNs)O(nrN_s) circuit executions for r≪nr\ll n, where NsN_s is the number of shots per queried entry. The central difficulty is that finite-shot errors perturb both the queried kernel values and the adaptive pivot sequence that determines the low-rank factor. We develop a non-asymptotic perturbation framework for this stochastic adaptive process, establishing concentration over the realized queries, stability of noisy pivot selection and factor construction, and propagation of the coupled sampling and approximation errors to the QSVM objective, optimizer, prediction function, and classification margin. The resulting rank–shot conditions characterize when ICAQKL approaches the full QSVM induced by the same quantum feature map. Experiments on benchmark and biomedical datasets show favorable accuracy–query-cost tradeoffs, competitive performance with the full QSVM, and competitive or improved performance relative to the evaluated Nyström baselines under comparable settings. ICAQKL is intended to enable measurement-efficient and theoretically controlled use of a selected quantum kernel, rather than to establish quantum advantage over classical kernels.

INTRODUCTION

Kernel methods provide a principled framework for supervised learning, combining nonlinear decision boundaries with convex training and a clear geometric interpretation through reproducing kernel Hilbert spaces (RKHS) Hofmann et al. [11]; Talitckii et al. [24]. In quantum machine learning, this perspective is particularly natural: a quantum feature map embeds a classical input into a quantum state, and pairwise similarities between the resulting states define a kernel that can subsequently be used by a classical kernel learner Havlíček et al. [9]; Schuld and Killoran [21]; Schuld [21]. This forms the foundation of quantum kernel methods and quantum support vector machines (QSVMs), a prominent paradigm for near-term quantum-enhanced supervised learning Havlíček et al. [9]; Schuld and Killoran [21]; Schuld [21].

A central practical limitation of quantum kernel learning (QKL) is the cost of acquiring the kernel matrix Thanaslip et al. [25]; Rodriguez-Grasa et al. [18]; Coelho et al. [3]. For nn training samples, a dense kernel method requires Θ(n2)\Theta(n^2) distinct pairwise similarities Schuld [21]. In the quantum setting, each non-trivial similarity is itself estimated from repeated circuit measurements rather than obtained as an inexpensive deterministic function evaluation. Consequently, with NsN_s shots per queried entry, dense kernel acquisition incurs Θ(n2Ns)\Theta(n^2N_s) circuit repetitions in addition to the O(n2)O(n^2) storage requirement Havlíček et al. [9]. For normalized fidelity kernels, the diagonal entries are known analytically, but the remaining n(n−1)/2n(n-1)/2 off-diagonal similarities still scale quadratically with the number of training examples. This measurement burden can dominate the cost of the learning pipeline and limits the size of datasets for which a dense QSVM is practical.

Low-rank kernel approximation provides a natural route to reducing this cost. Classical approaches include randomized matrix approximations, Random Fourier Features, Nyström methods, and Cholesky-type factorizations Mahoney [15]; Rahimi and Recht [17]; Hayakawa et al. [10]; Du et al. [5]. These methods were primarily developed for settings in which kernel entries can be accessed relatively cheaply and accurately. Their use with quantum kernels introduces an additional issue: the approximation algorithm itself determines which costly quantum similarities must be measured, while every such measurement is subject to finite-shot uncertainty. For example, a Nyström approximation queries similarities involving a selected landmark set, whereas pivoted Cholesky selects subsequent columns adaptively according to the residual structure of the approximation. Thus, in QKL, the low-rank approximation also acts as a query-allocation mechanism for a stochastic quantum-kernel oracle.

Motivated by this observation, we develop ICAQKL, a finite-shot adaptive low-rank framework for quantum kernel acquisition based on incomplete Cholesky factorization. We emphasize that pivoted incomplete Cholesky itself is a classical matrix approximation technique; our contribution is its formulation and analysis under adaptive finite-shot quantum-kernel access. Rather than constructing the dense Gram matrix, ICAQKL queries only the kernel entries required by the adaptively selected pivot columns and forms the rank-rr positive-semidefinite surrogate

K~rQ,(Ns)=G^r(Ns)(G^r(Ns))⊤.(1)\widetilde{K}_r^{Q,(N_s)} = \widehat{G}_r^{(N_s)}\left(\widehat{G}_r^{(N_s)}\right)^\top. \tag*{(1)}

Under symmetry, caching, and the analytically known fidelity diagonal, a rank-rr construction requires at most O(nr)O(nr) fresh quantum-kernel queries, compared with Θ(n2)\Theta(n^2) for dense acquisition. When r≪nr \ll n, this reduces the corresponding measurement count from Θ(n2Ns)\Theta(n^2N_s) to O(nrNs)O(nrN_s).

The main technical challenge is that finite-shot noise enters an adaptive recursive factorization. An entrywise concentration bound alone is insufficient: measurement error in an early queried entry can perturb the current Cholesky column, alter residual scores, change later pivots, and recursively propagate through the final low-rank factor. To address this difficulty, we introduce an exact-entry comparator that is constrained to follow the same pivot sequence selected by the finite-shot algorithm. This path-conditioned construction separates two fundamentally different sources of error: the structural rank-rr approximation error associated with the selected pivot path and the numerical perturbation induced by finite-shot kernel estimation.

Using this comparison, we develop a non-asymptotic perturbation analysis that begins with concentration for adaptively selected kernel queries, quantifies finite-shot perturbations of pivot scores and recursive Cholesky columns, and leads to a spectral error bound

Er(Ns):=∥KQ−K~rQ,(Ns)∥2≤εr(P^r)+(2βr+Δr)Δr,(2)\mathcal{E}_r^{(N_s)} := \left\|K^Q-\widetilde{K}_r^{Q,(N_s)}\right\|_2 \le\varepsilon_r(\widehat{P}_r)+(2\beta_r+\Delta_r)\Delta_r, \tag*{(2)}

where εr(P^r)\varepsilon_r(\widehat{P}_r) is the exact structural error along the selected pivot path, Δr\Delta_r measures the finite-shot factor perturbation, and βr\beta_r controls the norm of the corresponding exact path-conditioned factor. For a fixed stable rank, our analysis gives Δr=O(log⁡(Mr/δ)Ns)\Delta_r = O\left(\sqrt{\frac{\log(M_r/\delta)}{N_s}}\right) thereby making explicit how measurement precision and approximation rank enter the final kernel error.

We then propagate this kernel approximation through the complete QSVM learning problem. Rather than assuming a unique dual optimizer, we control the distance of the finite-shot solution to the exact optimal set under a quadratic-growth condition. The analysis further extends to previously unseen test points, where prediction requires only rr additional pivot–test kernel measurements. By accounting explicitly for the conditioning of the associated triangular Cholesky extension and for the SVM intercept, we obtain decision-function perturbation and margin-preservation guarantees. The resulting theory therefore provides an end-to-end chain from finite-shot quantum measurements, through adaptive low-rank kernel construction and QSVM optimization, to out-of-sample classification.

We evaluate ICAQKL on standard and biomedical classification benchmarks [14, 28, 29]. On capped subsets where dense quantum-kernel construction is tractable, ICAQKL closely tracks the predictive performance of the full QSVM while requiring substantially fewer kernel evaluations. We additionally compare against a Nyström-QSVM baseline and observe that the relative performance of the two low-rank constructions depends on the approximation rank: Nyström can provide lower reconstruction error at small ranks, whereas the residual-driven ICAQKL construction becomes competitive or more accurate in several larger-rank settings. Across the reported capped biomedical tasks at rank r=30r = 30, ICAQKL also provides a favorable measured accuracy–runtime trade-off relative to the evaluated Nyström implementation.

Our main contributions are summarized as follows:

  • Query-efficient adaptive quantum-kernel acquisition. We formulate ICAQKL as an adaptive incomplete-Cholesky construction under finite-shot quantum-kernel access, which requires O(nr)O(nr) fresh training-kernel queries through rank rr, compared with Θ(n2)\Theta(n^2) for dense kernel acquisition.

  • Finite-shot perturbation theory for adaptive factorization. We establish high-probability concentration for adaptively selected quantum-kernel queries in Theorem 1 and analyze how measurement noise propagates through residual scores, pivot selection, and recursively constructed Cholesky factors. The resulting path-conditioned bound in Theorem 2 separates structural low-rank approximation error from finite-shot perturbation.

  • End-to-end stability guarantees for QSVMs. We propagate finite-shot kernel perturbation via the complete learning problem. Theorem 3 establishes uniform QSVM dual-objective perturbation, exact-objective suboptimality, and, under quadratic growth, distance of finite-shot solution to the exact optimal set. We further derive out-of-sample kernel-vector, intercept-aware decision-function, and margin-preservation guarantees.

  • Empirical characterization of the accuracy–measurement trade-off. Experiments on standard and biomedical datasets show that ICAQKL remains close to dense QSVM performance on tractable matched subsets while substantially reducing the number of acquired kernel entries. Comparisons with the evaluated Nyström baseline characterize the rank-dependent trade-off between reconstruction quality, predictive accuracy, and measured runtime rather than asserting universal dominance of low-rank approximation method.

RELATED WORKS

Quantum kernel methods provide a direct connection between quantum feature maps and classical supervised learning. Early work shows that quantum devices can be used to estimate kernel functions associated with data embeddings in Hilbert space and combine them with classical SVMs Havlíček et al. [9]. Encoding data into quantum states can be interpreted as a nonlinear feature map, where inner products between quantum states naturally define kernels for classification Schuld and Killoran [21]. This has been later generalized by the observation that many supervised quantum learning models can be viewed as kernel methods Schuld [21].

Subsequent work has studied both the promise and the limitations of quantum kernels. Several studies have shown that their effectiveness depends strongly on the choice of embedding, the induced inductive bias, and the alignment between the kernel geometry and the target task structure [13, 12]. Recent analyses have also shown that quantum kernels may suffer from concentration and alignment issues, especially when chosen feature maps are not well suited to the data distribution, thereby limiting the effectiveness of the resulting classifier despite the high dimensionality of the underlying Hilbert space [22, 19] (Thanasilp et al. 2024). These results have increased attention to task alignment, sample efficiency, and the practical cost of kernel estimation.

Additionally, even when a quantum kernel is informative, training requires constructing an (n×n)(n \times n) Gram matrix, which becomes expensive as the dataset grows.

Studies have thus explored low-rank approximation and other resource-reduction strategies, including Nyström-based compression [4, 16] for quantum kernel target alignment and related kernel-construction [3, 23]. However, the quality of Nyström approximation depends strongly on the choice of landmark points and can deteriorate when the selected samples are not sufficiently representative of the full kernel matrix. Pivoted Cholesky decompositions provide an alternative that greedily selects pivots according to the residual structure of the matrix and constructs a factorization of the form K≈GGT\mathbf{K} \approx\mathbf{G}\mathbf{G}^{\mathsf{T}} [7, 8, 1]. Cholesky-type decompositions have been used as effective low-rank surrogates for dense PSD matrices, and recent work has studied pivoted Cholesky as a practical approximation tool for large kernel matrices with strong empirical and theoretical behavior [2, 6]. While low-rank approximation has recently been considered in scalable quantum kernel learning, existing work has mainly focused on Nyström-based methods; in contrast, we study adaptive incomplete Cholesky as a PSD-low-rank surrogate alternative.

PRELIMINARIES

This section introduces the quantum fidelity kernel and its finite-shot estimation model used throughout the paper. These definitions establish the exact and stochastic kernel objects that will later be distinguished in the ICAQKL construction.

Quantum feature maps and fidelity kernels. Quantum kernel methods embed a classical input x∈X⊆Rd\mathbf{x} \in\mathcal{X} \subseteq\mathbb{R}^{d} into a complex high-dimensional Hilbert space H\mathcal{H} via a data-dependent unitary, Uϕ:X→U(2q)U_{\phi} : \mathcal{X} \to U(2^{q}), where U(2q)U(2^{q}) is the unitary group on qq qubits, U(2q)={U∈C2q×2q∣U†U=UU†=I}U(2^{q}) = \{U \in\mathbb{C}^{2^{q} \times2^{q}} \mid U^{\dagger}U = UU^{\dagger} = \mathbf{I}\}. The corresponding quantum feature state is obtained by applying Uϕ(x)U_{\phi}(\mathbf{x}) to the computational basis state, i.e., ∣ϕ(x)⟩=Uϕ(x)∣0⟩⊗q\lvert\phi(\mathbf{x})\rangle= U_{\phi}(\mathbf{x})\lvert0\rangle^{\otimes q}. Since dim⁡(H)=2q\dim(\mathcal{H}) = 2^{q}, this embedding induces a feature space whose dimension grows exponentially with the number of qubits qq. The geometry of this space is characterized by the embedded states {∣ϕ(x)⟩}x∈X\{\lvert\phi(\mathbf{x})\rangle\}_{\mathbf{x}\in\mathcal{X}}, with pairwise similarity measured by their fidelity, where larger fidelity indicates greater similarity, while smaller fidelity indicates stronger separation.

Definition 1 (Quantum fidelity kernel). For xi,xj∈X\mathbf{x}_{i}, \mathbf{x}_{j} \in\mathcal{X} with feature states ∣ϕ(xi)⟩\lvert\phi(\mathbf{x}_{i})\rangle and ∣ϕ(xj)⟩\lvert\phi(\mathbf{x}_{j})\rangle, the fidelity-based quantum kernel is defined as kQ(xi,xj)=∣⟨ϕ(xj)∣ϕ(xi)⟩∣2=Tr⁡[ρϕ(xi)ρϕ(xj)]k^{\mathrm{Q}}(\mathbf{x}_{i},\mathbf{x}_{j}) = \left|\langle\phi(\mathbf{x}_{j}) \mid\phi(\mathbf{x}_{i})\rangle\right|^{2} = \operatorname{Tr}[\rho_{\phi}(\mathbf{x}_{i})\rho_{\phi}(\mathbf{x}_{j})].

This kernel measures similarity in the quantum feature space and is symmetric and positive semidefinite (PSD), enabling its use in kernel methods such as support vector machines (SVMs). For a dataset {xi}i=1n\{x_i\}_{i=1}^{n}, the corresponding quantum Gram matrix KQ∈Rn×n\mathbf{K}^{Q} \in\mathbb{R}^{n \times n} is defined by KijQ=κQ(xi,xj)K_{ij}^{Q}=\kappa^{Q}(x_i,x_j).

Finite shot-based kernel estimation. On quantum hardware, kernel entries are not computed exactly but estimated through repeated circuit executions. We adopt an overlap-based estimation procedure that avoids the ancilla qubits and controlled-SWAP operations Volkoff and Subaşı [26] required by SWAP-test methods. In particular, each kernel value is κQ(xi,xj)=∣⟨0∣⊗qUϕ†(xj)Uϕ(xi)∣0⟩⊗q∣2\kappa^{Q}(x_i,x_j)=\left|\langle0|^{\otimes q}U_{\phi}^{\dagger}(x_j)U_{\phi}(x_i)|0\rangle^{\otimes q}\right|^2. Let Xs(ij)∈{0,1}X_s^{(ij)} \in\{0,1\}, s=1,…,Nss=1,\ldots,N_s indicate whether the ssth circuit execution returns the all-zero outcome. Under the finite-shot sampling model, Xs(ij)∼i.i.d.Bernoulli⁡(κQ(xi,xj))X_s^{(ij)} \overset{\mathrm{i.i.d.}}{\sim} \operatorname{Bernoulli}\left(\kappa^{Q}(x_i,x_j)\right). The empirical quantum-kernel estimator is therefore

κ^NsQ(xi,xj):=1Ns∑s=1NsXs(ij).\widehat{\kappa}_{N_s}^{Q}(x_i,x_j):=\frac{1}{N_s}\sum_{s=1}^{N_s}X_s^{(ij)}.

Proposition 1 (Finite-shot overlap estimator). For any x,x′∈Xx,x' \in\mathcal{X}, let κ^NsQ(x,x′)\widehat{\kappa}_{N_s}^{Q}(x,x') denote the empirical estimator obtained from NsN_s independent circuit repetitions, defined as the empirical frequency of observing the all-zero outcome. Then, it is unbiased and satisfies E[κ^NsQ(x,x′)]=κQ(x,x′)\mathbb{E}\left[\widehat{\kappa}_{N_s}^{Q}(x,x')\right]=\kappa^{Q}(x,x') and Var⁡(κ^NsQ(x,x′))=κQ(x,x′)(1−κQ(x,x′))Ns\operatorname{Var}\left(\widehat{\kappa}_{N_s}^{Q}(x,x')\right)=\frac{\kappa^{Q}(x,x')\left(1-\kappa^{Q}(x,x')\right)}{N_s}.

Thus, the estimator is unbiased, with standard error scaling as O(Ns−1/2)O(N_s^{-1/2}), implying that accurate kernel estimation may require a large number of measurements.

Computational bottleneck: Given nn training samples, a symmetric n×nn \times n Gram matrix contains n(n+1)/2n(n+1)/2 distinct upper-triangular entries. For the normalized fidelity kernel, however, the nn diagonal entries satisfy KiiQ=1K_{ii}^{Q}=1 analytically. Hence dense finite-shot acquisition requires n(n−1)/2n(n-1)/2 fresh off-diagonal quantum-kernel queries. With NsN_s shots per entry, the total number of circuit executions scales as O(n2Ns)O(n^2N_s), which quickly becomes prohibitive as the dataset size increases. Since each evaluation involves executing both UϕU_{\phi} and Uϕ†U_{\phi}^{\dagger}, the runtime additionally depends on circuit depth and hardware execution cost. This quadratic scaling in nn is a primary computational bottleneck of QKL and motivates the scalable low-rank approximation framework developed in the next section.

METHODOLOGY

We now present ICAQKL, a query-efficient framework for quantum kernel learning under finite-shot access. The pivoted incomplete-Cholesky mechanism underlying the low-rank construction is classical; our focus is instead on how such an adaptive construction behaves when every required quantum-kernel entry must be estimated from stochastic circuit measurements. This distinction is important because finite-shot estimation affects not only individual kernel values, but also the residual scores that determine future pivots and the recursively constructed Cholesky factor.

Accordingly, our analysis separates an exact-entry comparator from the actual finite-shot ICAQKL recursion. The exact comparator follows a prescribed pivot sequence using the ideal quantum kernel and therefore retains the usual positive-semidefinite Cholesky residual structure. The finite-shot recursion instead operates on noisy overlap estimates. Although its constructed surrogate remains positive semidefinite by construction, its residual relative to the ideal kernel need not be positive semidefinite. This separation enables us to isolate structural low-rank approximation error from finite-shot numerical error and propagate both effects to the final QSVM classifier.

Finite-Shot Adaptive Quantum-Kernel Factorization

References

  1. [1]Francis Bach. Sharp analysis of low-rank kernel matrix approximations. In Proceedings of the International Conference on Learning Theory (COLT), volume 30, pages 1–25. JMLR, 2013.arxiv.org/abs/1208.2015
  2. [2]Yifan Chen, Ethan N. Epperly, Joel A. Tropp, and Robert J. Webber. Randomly pivoted cholesky: Practical approximation of a kernel matrix with few entry evaluations. Communications on Pure and Applied Mathematics, 78:995–1041, 2025. doi: 10.1002/cpa.22234.DOI
  3. [3]Rodrigo Coelho, Georg Kruse, and Andreas Rosskopf. Quantum-efficient kernel target alignment, Feb. 2025. URL https://arxiv.org/abs/2502.08225.
  4. [4]Petros Drineas and Michael W. Mahoney. On the nyström method for approximating a gram matrix for improved kernel-based learning. Journal of Machine Learning Research, 6(72):2153–2175, Dec. 2005. URL https://jmlr.org/papers/v6/drineas05a.html.
  5. [5]Jinda Du, Jian Hou, and Huaqiang Yuan. Improving nyström spectral clustering with unsupervised vector quantization and incomplete cholesky decomposition. In PRICAI 2025: Trends in Artificial Intelligence, volume 16451 of Lecture Notes in Computer Science, pages 155–170. Springer, Singapore, 2026. doi: 10.1007/978-981-95-7075-1_10. URL https://doi.org/10.1007/978-981-95-7075-1_10.
  6. [6]Ethan N. Epperly, Joel A. Tropp, and Robert J. Webber. Embrace rejection: Kernel matrix approximation by accelerated randomly pivoted cholesky. SIAM Journal on Matrix Analysis and Applications, 46(4):2527–2557, 2025. doi: 10.1137/24M1699048. URL https://doi.org/10.1137/24M1699048.
  7. [7]Shai Fine and Katya Scheinberg. Efficient svm training using low-rank kernel representations. Journal of Machine Learning Research, 2(Mar):243–264, Mar. 2002. URL https://jmlr.org/papers/v2/fine01a.html.
  8. [8]Helmut Harbrecht, Michael Peters, and Reinhold Schneider. On the low-rank approximation by the pivoted cholesky decomposition. Applied Numerical Mathematics, 62(4):428–440, Apr. 2012. doi: 10.1016/j.apnum.2011.10.001. URL https://doi.org/10.1016/j.apnum.2011.10.001.
  9. [9]Vojtěch Havlíček, Antonio D. Córcoles, Kristan Temme, Aram W. Harrow, Abhinav Kandala, Jerry M. Chow, and Jay M. Gambetta. Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747):209–212, Mar. 2019. doi: 10.1038/s41586-019-0980-2. URL https://doi.org/10.1038/s41586-019-0980-2.
  10. [10]Satoshi Hayakawa, Harald Oberhauser, and Terry Lyons. Sampling-based nystrom approximation and kernel quadrature, 2023. URL https://arxiv.org/abs/2301.09517.
  11. [11]Thomas Hofmann, Bernhard Schölkopf, and Alex Smola. Kernel methods in machine learning. Annals of Statistics, 36(3):1171–1220, Jun. 2008. doi: 10.1214/009053607000000677. URL https://doi.org/10.1214/009053607000000677.
  12. [12]Hsin-Yuan Huang, Michael Broughton, Masoud Mohseni, Ryan Babbush, Sergio Boixo, Hartmut Neven, and Jarrod R. McClean. Power of data in quantum machine learning. Nature Communications, 12(2631), May 2021. doi: 10.1038/s41467-021-22539-9. URL https://doi.org/10.1038/s41467-021-22539-9.
  13. [13]Jonas M. Kübler, Simon Buchholz, and Bernhard Schölkopf. The inductive bias of quantum kernels. In Proceedings of the 35th International Conference on Neural Information Processing Systems, pages 12661–12673. Curran Associates, Inc., 2021.arxiv.org/abs/2106.03747
  14. [14]Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998. doi: 10.1109/5.726791.
  15. [15]Michael W. Mahoney. Randomized algorithms for matrices and data. Foundations and Trends in Machine Learning, 3(2):123–224, Feb. 2011. doi: 10.1561/2200000035. URL https://doi.org/10.1561/2200000035.
  16. [16]Cameron Musco and Christopher Musco. Recursive sampling for the nystrom method. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.arxiv.org/abs/1605.07583
  17. [17]Ali Rahimi and Benjamin Recht. Random features for large-scale kernel machines. In Advances in Neural Information Processing Systems, volume 20, page 1177–1184. Curran Associates, Inc., 2007.
  18. [18]Pablo Rodriguez-Grasa, Yue Ban, and Mikel Sanz. Neural quantum kernels: Training quantum kernels with quantum neural networks. Physical Review Research, 7(2):023269, Jun. 2025. doi: 10.1103/xphb-x2g4. URL https://link.aps.org/doi/10.1103/xphb-x2g4.DOI
  19. [19]Jan Schnabel and Marco Roth. Quantum kernel methods under scrutiny: A benchmarking study. Quantum Machine Intelligence, 7(58), Apr. 2025. doi: 10.1007/s42484-025-00273-5. URL https://doi.org/10.1007/s42484-025-00273-5.
  20. [21]Maria Schuld and Nathan Killoran. Quantum machine learning in feature hilbert spaces. Physical Review Letters, 122(4):040504, Feb. 2019. doi: 10.1103/PhysRevLett.122.040504. URL https://link.aps.org/doi/10.1103/PhysRevLett.122.040504.
  21. [22]Ruslan Shaydulin and Stefan Wild. Importance of kernel bandwidth in quantum machine learning. Phys. Rev. A, 106:042407, Oct. 2022. doi: 10.1103/PhysRevA.106.042407. URL https://link.aps.org/doi/10.1103/PhysRevA.106.042407.DOI
  22. [23]Utkarsh Singh, Jean-Frédéric Laprade, Aaron Z. Goldberg, and Khabat Heshami. A resource efficient quantum kernel, 2026. URL https://arxiv.org/abs/2507.03689.
  23. [24]Aleksandr Talitckii, Brendon Colbert, and Matthew M. Peet. Efficient convex algorithms for universal kernel learning. Journal of Machine Learning Research, 25(203):1–40, 2024. URL https://www.jmlr.org/papers/v25/23-0528.html.arxiv.org/abs/2304.07472
  24. [25]Supanut Thanaslip, Samson Wang, M. Cerezo, and Zoë Holmes. Exponential concentration in quantum kernel methods. Nature Communications, 15(5200), Jun. 2024. doi: 10.1038/s41467-024-49287-w. URL https://doi.org/10.1038/s41467-024-49287-w.
  25. [26]T. J. Volkoff and Yiğit Subaşı. Ancilla-free continuous-variable SWAP test. Quantum, 6:800, Sep. 2022. doi: 10.22331/q-2022-09-08-800. URL https://doi.org/10.22331/q-2022-09-08-800.
  26. [27]William H. Wolberg, W. Nick Street, and Olvi L. Mangasarian. Wisconsin diagnostic breast cancer (wdbc). UCI Machine Learning Repository, 1993. URL https://doi.org/10.24432/C5DW2B.
  27. [28]Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms, 2017. URL https://arxiv.org/abs/1708.07747.
  28. [29]Jiancheng Yang, Rui Shi, Donglai Wei, et al. Medmnist v2: A large-scale lightweight benchmark for 2d and 3d biomedical image classification. Scientific Data, 10(1):41, Jan. 2023. doi: 10.1038/s41597-022-01721-8. URL https://doi.org/10.1038/s41597-022-01721-8.

Paper details

vlnc:W_jsnqrgdv
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Engineering

Not recorded for this paper

View statement
Looking for related papers…
Contents