pith. machine review for the scientific record. sign in

arxiv: 2604.19076 · v1 · submitted 2026-04-21 · 🪐 quant-ph

Recognition: unknown

Towards Automated Selection of Quantum Encoding Circuits via Meta-Learning

Dao Duy Tung, Lan Nguyen Tran, Le Bin Ho, Nguyen Quoc Chuong, Vu Tuan Hai

Authors on Pith no claims yet

Pith reviewed 2026-05-10 03:10 UTC · model grok-4.3

classification 🪐 quant-ph
keywords quantum kernel methodsencoding circuitsmeta-learningdata complexity metricscircuit selectionquantum machine learningautomated recommendation
0
0 comments X

The pith

Classical complexity metrics can select the best quantum encoding circuit for a dataset without any quantum computation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows how to automate the choice of quantum encoding circuits using only classical data properties. It tests nine possible circuits and 24 different complexity measures from the data. Two different meta-learning methods are trained on these measures to predict which circuit will perform best on quantum kernel tasks. Both methods reach up to 85.7 percent top-3 accuracy in picking the right circuit. This means future users could skip expensive trials on quantum hardware and go straight to the likely best encoding.

Core claim

By treating circuit selection as a meta-learning task, the authors demonstrate that 24 classical dataset complexity metrics suffice to train machine learning models that identify high-performing quantum encoding circuits with top-3 accuracy reaching 85.7 percent across multiple configurations.

What carries the argument

A meta-learning recommender that uses 24 classical complexity metrics as input features to predict the best among nine quantum encoding circuits.

If this is right

  • Quantum kernel methods become more practical on near-term devices by avoiding repeated quantum evaluations for circuit choice.
  • Classical data analysis alone can guide quantum circuit design for specific datasets.
  • Automated tools could standardize encoding selection across different quantum machine learning applications.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar approaches might work for selecting other quantum circuit components beyond encodings.
  • Expanding the set of candidate circuits could improve accuracy if the current nine do not cover all useful options.
  • Testing on datasets from diverse domains would check if the predictive power holds beyond the studied cases.

Load-bearing premise

That the chosen 24 classical complexity metrics capture the dataset features that decide which encoding circuit will actually perform best.

What would settle it

Evaluating the predicted best circuit on a new dataset and finding that a different circuit from the nine actually gives higher quantum kernel performance.

read the original abstract

In recent years, quantum kernel methods have shown promising applications on near-term quantum devices. However, selecting an appropriate encoding circuit for a given dataset requires costly evaluation of multiple candidates, formulated as a meta-learning problem. In this paper, we propose an automated recommender that utilizes the intrinsic characteristics of datasets to predict the optimal circuit without any quantum evaluation. Nine candidates are assessed alongside 24 classical complexity metrics serving as features, evaluated through two training approaches with four configurations, along with 14 machine learning models. Both approaches achieve Top-3 accuracy of up to 85.7% in identifying the best-performing encoding circuit, and demonstrate that classical data complexity metrics provide sufficient predictive signal for circuit selection.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The manuscript proposes a meta-learning recommender system for selecting quantum encoding circuits in kernel methods. It evaluates nine fixed candidate circuits on datasets using 24 classical complexity metrics (e.g., dimensionality, separability) as input features, trains 14 classical ML models under two approaches and four configurations, and reports that both approaches reach top-3 accuracy of up to 85.7% in identifying the best-performing circuit without any quantum evaluations.

Significance. If the empirical mapping from classical metrics to circuit performance generalizes, the work could reduce the computational cost of circuit selection for near-term quantum ML by replacing repeated quantum evaluations with a classical predictor. The approach is pragmatic and directly addresses a practical bottleneck in variational and kernel-based quantum algorithms.

major comments (3)
  1. [§4] §4 (Experiments and Results): The central claim that the 24 classical metrics supply sufficient predictive signal rests on top-3 accuracy within a closed set of nine circuits and an unspecified collection of datasets. No ablation is reported that removes quantum-specific performance labels or tests the learned mapping on circuits outside the original nine, leaving open whether accuracy reflects genuine dataset-circuit geometry interactions or merely memorization of the narrow candidate pool.
  2. [§3.2] §3.2 (Dataset and Labeling Procedure): The manuscript does not specify the number, size, or diversity of the datasets used to generate the performance labels, nor the exact quantum metric (accuracy, kernel alignment, etc.) employed to rank the nine circuits. Without these details, it is impossible to judge whether the reported 85.7% accuracy is robust to dataset scale or to variations in how “best circuit” is defined.
  3. [Table 2] Table 2 (or equivalent results table): The accuracy figures are presented as single point estimates without confidence intervals, standard deviations across random seeds, or explicit cross-validation folds. This omission makes it difficult to determine whether the performance difference between the two training approaches is statistically meaningful or sensitive to overfitting on the limited meta-dataset.
minor comments (2)
  1. [Abstract] The abstract and §1 cite “up to 85.7%” top-3 accuracy but do not clarify whether this is the maximum across all 14 models or a specific configuration; a single clarifying sentence would improve readability.
  2. [§3.1] Notation for the 24 complexity metrics is introduced in §3.1 but never tabulated with explicit formulas or references to the original complexity-measure papers; adding such a table would aid reproducibility.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. We address each major comment point by point below and have revised the manuscript to enhance clarity and address the raised concerns.

read point-by-point responses

  1. Referee: [§4] §4 (Experiments and Results): The central claim that the 24 classical metrics supply sufficient predictive signal rests on top-3 accuracy within a closed set of nine circuits and an unspecified collection of datasets. No ablation is reported that removes quantum-specific performance labels or tests the learned mapping on circuits outside the original nine, leaving open whether accuracy reflects genuine dataset-circuit geometry interactions or merely memorization of the narrow candidate pool.

    Authors: Our work targets the practical task of recommending the best circuit from a fixed set of nine candidates using only classical metrics, thereby avoiding quantum evaluations at inference time. The top-3 accuracies substantially exceed the random baseline of 33%, indicating that the metrics encode meaningful dataset-circuit relationships rather than mere memorization of the candidate pool. While we recognize that evaluating the meta-learner on entirely new circuits would provide additional evidence of generalization, this would necessitate generating fresh quantum performance labels and lies beyond the scope of the present study. In the revised manuscript we have added a dedicated limitations paragraph in §4 that explicitly discusses the fixed-candidate setting and identifies generalization to unseen circuits as an important direction for future research. revision: partial

  2. Referee: [§3.2] §3.2 (Dataset and Labeling Procedure): The manuscript does not specify the number, size, or diversity of the datasets used to generate the performance labels, nor the exact quantum metric (accuracy, kernel alignment, etc.) employed to rank the nine circuits. Without these details, it is impossible to judge whether the reported 85.7% accuracy is robust to dataset scale or to variations in how “best circuit” is defined.

    Authors: We have revised §3.2 to provide the missing details: the exact number of datasets, their sources, size ranges, and diversity characteristics are now stated explicitly, together with the precise quantum metric (test accuracy of a quantum support-vector machine) and the ranking procedure (highest average accuracy over multiple random train-test splits). A summary table has also been added for clarity. revision: yes

  3. Referee: [Table 2] Table 2 (or equivalent results table): The accuracy figures are presented as single point estimates without confidence intervals, standard deviations across random seeds, or explicit cross-validation folds. This omission makes it difficult to determine whether the performance difference between the two training approaches is statistically meaningful or sensitive to overfitting on the limited meta-dataset.

    Authors: We agree that variability measures are necessary for assessing reliability. Table 2 has been updated to report mean top-3 accuracies together with standard deviations computed across the cross-validation folds and the random seeds used for both the meta-learners and the quantum evaluations. The revised table shows that the performance differences remain consistent and that the results are not overly sensitive to particular data splits. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical meta-learning validation is self-contained

full rationale

The paper's core contribution is an empirical meta-learning pipeline: 24 classical dataset complexity metrics are computed as input features, 14 ML models are trained under two approaches to map these features to the best-performing circuit among nine fixed candidates, and success is measured by Top-3 accuracy (up to 85.7%) on held-out evaluations whose labels come from separate quantum performance runs. No equations, ansatzes, or derivations are present that reduce the reported accuracy or the sufficiency claim to a fitted parameter defined by the target itself, a self-citation chain, or a renaming of the input. The demonstration therefore rests on independent measurement rather than tautological construction, satisfying the default expectation of a non-circular empirical study.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review is limited to the abstract; no explicit free parameters, new entities, or non-standard axioms are stated. The work rests on the domain assumption that classical metrics suffice to predict quantum circuit utility.

axioms (1)
  • domain assumption Classical data complexity metrics are sufficient to predict which quantum encoding circuit will perform best for a given dataset
    This is the central hypothesis that enables the meta-learning approach described in the abstract.

pith-pipeline@v0.9.0 · 5418 in / 1253 out tokens · 52668 ms · 2026-05-10T03:10:59.870551+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

51 extracted references · 45 canonical work pages · 1 internal anchor

  1. [1]

    Ciliberto, M

    Ciliberto, C., Herbster, M., Ialongo, A.D., Pontil, M., Rocchetto, A., Severini, S., Wossnig, L.: Quantum machine learning: a classical perspective. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences474(2209), 20170551 (2018) https://doi.org/10.1098/rspa.2017.0551 14 𝑅!(𝒙) (a) ×𝐿 (b) ×𝐿 ⊕⊕⊕ 𝐻 (c) ×𝐿 𝑃(2𝒙) (d) ⊕𝑃𝑥",𝑥#⊕ 𝑃2𝜋−...

    work page doi:10.1098/rspa.2017.0551 2018

  2. [2]

    Information Science and Statistics

    Bishop, C.M.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, New York (2006)

    2006

  3. [3]

    SIAM Review60(2), 223–311 (2018) https://doi.org/10.1137/ 16M1080173

    Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Review60(2), 223–311 (2018) https://doi.org/10.1137/ 16M1080173

    2018

  4. [4]

    SIAM Journal on Computing26(5), 1484–1509 (1997) https: //doi.org/10.1137/s0097539795293172

    Shor, P.W.: Polynomial-time algorithms for prime factorization and discrete log- arithms on a quantum computer. SIAM Journal on Computing26(5), 1484–1509 (1997) https://doi.org/10.1137/S0097539795293172

    work page doi:10.1137/s0097539795293172 1997

  5. [5]

    A fast quantum mechanical algorithm for database search,

    Grover, L.K.: A fast quantum mechanical algorithm for database search. In: 16 T able B2Properties of the encoding circuits and their abbreviation used in this study (L= 2 layers). Circuit Abbr. #Params #Gates Depth 2-qubit gate SeparableRx SRx 0 8 2 - HardwareEfficientRx HERx 0 14 8 CX ZFeatureMap ZFM 0 16 4 - ZZFeatureMap ZZFM 0 34 22 CX HighDim HD 0 31 ...

    work page doi:10.1145/237814.237866 1996

  6. [6]

    https://doi.org/10.48550/arXiv.1512.02900

    Adcock, J., Allen, E., Day, M., Frick, S., Hinchliff, J., Johnson, M., Morley-Short, S., Pallister, S., Price, A., Stanisic, S.: Advances in quantum machine learning (2015). https://doi.org/10.48550/arXiv.1512.02900

    work page doi:10.48550/arxiv.1512.02900 2015

  7. [7]

    Nature549(7671), 195–202 (2017) https://doi.org/10.1038/nature23474

    Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., Lloyd, S.: Quantum machine learning. Nature549(7671), 195–202 (2017) https://doi.org/ 10.1038/nature23474 17

    work page doi:10.1038/nature23474 2017

  8. [8]

    A rigorous and robust quantum speed-up in supervised machine learning

    Liu, Y., Arunachalam, S., Temme, K.: A rigorous and robust quantum speed-up in supervised machine learning. Nature Physics17(9), 1013–1017 (2021) https: //doi.org/10.1038/s41567-021-01287-z

    work page doi:10.1038/s41567-021-01287-z 2021

  9. [9]

    The power of quantum neural networks,

    Abbas, A., Sutter, D., Zoufal, C., Lucchi, A., Figalli, A., Woerner, S.: The power of quantum neural networks. Nature Computational Science1(6), 403–409 (2021) https://doi.org/10.1038/s43588-021-00084-1

    work page doi:10.1038/s43588-021-00084-1 2021

  10. [10]

    Nature Communications14(1), 4006 (2023) https: //doi.org/10.1038/s41467-023-39785-8

    Pan, X., Lu, Z., Wang, W., Hua, Z., Xu, Y., Li, W., Cai, W., Li, X., Wang, H., Song, Y.-P., Zou, C.-L., Deng, D.-L., Sun, L.: Deep quantum neural networks on a superconducting processor. Nature Communications14(1), 4006 (2023) https: //doi.org/10.1038/s41467-023-39785-8

    work page doi:10.1038/s41467-023-39785-8 2023

  11. [11]

    ACM Comput

    Massoli, F.V., Vadicamo, L., Amato, G., Falchi, F.: A leap among quantum com- puting and quantum neural networks: A survey. ACM Comput. Surv.55(5) (2022) https://doi.org/10.1145/3529756

    work page doi:10.1145/3529756 2022

  12. [12]

    Nature Communications5(1), 4213 (2014) https://doi.org/ 10.1038/ncomms5213

    Peruzzo, A., McClean, J., Shadbolt, P., Yung, M.-H., Zhou, X.-Q., Love, P.J., Aspuru-Guzik, A., O’Brien, J.L.: A variational eigenvalue solver on a photonic quantum processor. Nature Communications5(1), 4213 (2014) https://doi.org/ 10.1038/ncomms5213

    work page doi:10.1038/ncomms5213 2014

  13. [13]

    Larocca, S

    Larocca, M., Thanasilp, S., Wang, S., Sharma, K., Biamonte, J., Coles, P.J., Cincio, L., McClean, J.R., Holmes, Z., Cerezo, M.: Barren plateaus in variational quantum computing. Nature Reviews Physics7(4), 174–189 (2025) https://doi. org/10.1038/s42254-025-00813-9

    work page doi:10.1038/s42254-025-00813-9 2025

  14. [14]

    Cerezoet al., Variational quantum al- gorithms, Nat

    Cerezo, M., Arrasmith, A., Babbush, R., Benjamin, S.C., Endo, S., Fujii, K., McClean, J.R., Mitarai, K., Yuan, X., Cincio, L., Coles, P.J.: Variational quan- tum algorithms. Nature Reviews Physics3(9), 625–644 (2021) https://doi.org/ 10.1038/s42254-021-00348-9

    work page doi:10.1038/s42254-021-00348-9 2021

  15. [15]

    Schuld, M., Killoran, N.: Quantum machine learning in feature hilbert spaces. Phys. Rev. Lett.122, 040504 (2019) https://doi.org/10.1103/PhysRevLett.122. 040504

    work page doi:10.1103/physrevlett.122 2019

  16. [16]

    Supervised quantum machine learning mod- els are kernel methods

    Schuld, M.: Supervised quantum machine learning models are kernel methods (2021). https://doi.org/10.48550/arXiv.2101.11020

    work page doi:10.48550/arxiv.2101.11020 2021

  17. [17]

    IEEE Transactions on Emerging Topics in Computational Intelligence, 1–10 (2024) https://doi.org/10

    Incudini, M., Bosco, D.L., Martini, F., Grossi, M., Serra, G., Pierro, A.D.: Automatic and effective discovery of quantum kernels. IEEE Transactions on Emerging Topics in Computational Intelligence, 1–10 (2024) https://doi.org/10. 1109/TETCI.2024.3499993

    work page arXiv 2024

  18. [18]

    https://doi.org/10.48550/arXiv.2502.15129 18

    Paula Neto, F.M.: Data Complexity Measures for Quantum Circuits Architecture Recommendation (2025). https://doi.org/10.48550/arXiv.2502.15129 18

    work page doi:10.48550/arxiv.2502.15129 2025

  19. [19]

    Neurocomputing521, 126– 136 (2023) https://doi.org/10.1016/j.neucom.2022.11.056

    Komorniczak, J., Ksieniewicz, P.: problexity-an open-source python library for supervised learning problem complexity assessment. Neurocomputing521, 126– 136 (2023) https://doi.org/10.1016/j.neucom.2022.11.056

    work page doi:10.1016/j.neucom.2022.11.056 2023

  20. [20]

    Lorena, A.C., Garcia, L.P.F., Lehmann, J., Souto, M.C.P., Ho, T.K.: How complex is your classification problem? a survey on measuring classification complexity 52(5) (2019) https://doi.org/10.1145/3347711

    work page doi:10.1145/3347711 2019

  21. [21]

    Machine Learning: Science and Technology3(1), 015034 (2022) https://doi.org/10.1088/ 2632-2153/ac5997

    Nguyen, Q.C., Ho, L.B., Nguyen Tran, L., Nguyen, H.Q.: Qsun: an open-source platform towards practical quantum machine learning applications. Machine Learning: Science and Technology3(1), 015034 (2022) https://doi.org/10.1088/ 2632-2153/ac5997

    2022

  22. [22]

    IEEE Transactions on Pattern Analysis and Machine Intelligence20(3), 226–239 (1998) https://doi.org/10.1109/34.667881

    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence20(3), 226–239 (1998) https://doi.org/10.1109/34.667881

    work page doi:10.1109/34.667881 1998

  23. [23]

    In: Proceedings of the 14th International Joint Conference on Artificial Intelligence - Volume 2

    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence - Volume 2. IJCAI’95, pp. 1137–1143. Morgan Kauf- mann Publishers Inc., San Francisco, CA, USA (1995). https://doi.org/10.5555/ 1643031.1643047

    work page arXiv 1995

  24. [24]

    IEEE Transactions on Pattern Analysis and Machine Intelligence24(3), 289–300 (2002) https://doi.org/10.1109/34.990132

    Ho, T.K., Basu, M.: Complexity measures of supervised classification problems. IEEE Transactions on Pattern Analysis and Machine Intelligence24(3), 289–300 (2002) https://doi.org/10.1109/34.990132

    work page doi:10.1109/34.990132 2002

  25. [25]

    Actas del III Taller Nacional de Mineria de Datos y Aprendizaje1, 18–44 (2005)

    Sotoca, J.M., S´ anchez, J.S., Mollineda, R.A.: A review of data complexity mea- sures and their applicability to pattern classification problems. Actas del III Taller Nacional de Mineria de Datos y Aprendizaje1, 18–44 (2005)

    2005

  26. [26]

    Proceedings of the Royal Society of London

    Mercer, J.: Functions of positive and negative type, and their connection with the theory of integral equations. Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character83(559), 69–70 (1909) https://doi.org/10.1098/rspa.1909.0075

    work page doi:10.1098/rspa.1909.0075 1909

  27. [27]

    Boser and Isabelle Guyon and Vladimir Vapnik , editor =

    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal mar- gin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory. COLT ’92, pp. 144–152. Association for Computing Machinery, New York, NY, USA (1992). https://doi.org/10.1145/130385.130401

    work page doi:10.1145/130385.130401 1992

  28. [28]

    Hubregtsen, T., Wierichs, D., Gil-Fuster, E., Derks, P.-J.H.S., Faehrmann, P.K., Meyer, J.J.: Training quantum embedding kernels on near-term quantum com- puters. Phys. Rev. A106, 042431 (2022) https://doi.org/10.1103/PhysRevA.106. 042431

    work page doi:10.1103/physreva.106 2022

  29. [29]

    Na- ture Communications12(1), 2631 (2021) https: //doi.org/10.1038/s41467-021-22539-9

    Huang, H.-Y., Broughton, M., Mohseni, M., Babbush, R., Boixo, S., Neven, H., 19 McClean, J.R.: Power of data in quantum machine learning. Nature Communi- cations12(1), 2631 (2021) https://doi.org/10.1038/s41467-021-22539-9

    work page doi:10.1038/s41467-021-22539-9 2021

  30. [30]

    Machine Learning , year =

    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning20(3), 273– 297 (1995) https://doi.org/10.1007/BF00994018

    work page doi:10.1007/bf00994018 1995

  31. [31]

    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning, pp. 1–244. The MIT Press, Cambridge, MA (2005). https://doi.org/10.7551/ mitpress/3206.001.0001

    2005

  32. [32]

    In: Proceedings of the Fifteenth International Conference on Machine Learning

    Saunders, C., Gammerman, A., Vovk, V.: Ridge regression learning algorithm in dual variables. In: Proceedings of the Fifteenth International Conference on Machine Learning. ICML ’98, pp. 515–521. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1998). https://doi.org/10.5555/645527.657464

    work page doi:10.5555/645527.657464 1998

  33. [33]

    Journal of Machine Learning Research12, 2825–2830 (2011) https://doi.org/10.5555/1953048

    Pedregosa, F.e.a.: Scikit-learn: Machine learning in Python. Journal of Machine Learning Research12, 2825–2830 (2011) https://doi.org/10.5555/1953048. 2078195

    work page doi:10.5555/1953048 2011

  34. [34]

    In: Proceedings of the Annual Symposium on Computer Application in Medical Care, pp

    Smith, J.W., Everhart, J.E., Dickson, W.C., Knowler, W.C., Johannes, R.S.: Using the adap learning algorithm to forecast the onset of diabetes mellitus. In: Proceedings of the Annual Symposium on Computer Application in Medical Care, pp. 261–265 (1988). Published November 9, 1988

    1988

  35. [35]

    UCI Machine Learning Repository (2012)

    Lohweg, V.: Banknote Authentication. UCI Machine Learning Repository (2012). https://doi.org/10.24432/C55P57

    work page doi:10.24432/c55p57 2012

  36. [36]

    UCI Machine Learning Repository (1976)

    Haberman, S.: Haberman’s Survival. UCI Machine Learning Repository (1976). https://doi.org/10.24432/C5XK51

    work page doi:10.24432/c5xk51 1976

  37. [37]

    https://doi.org/10.48550/arXiv.2509.16410

    Pere, C.: Data Complexity: a threshold between Classical and Quantum Machine Learning – Part I (2025). https://doi.org/10.48550/arXiv.2509.16410

    work page doi:10.48550/arxiv.2509.16410 2025

  38. [38]

    Canatar, E

    Canatar, A., Peters, E., Pehlevan, C., Wild, S.M., Shaydulin, R.: Bandwidth enables generalization in quantum kernel models. Transactions on Machine Learning Research (2023) https://doi.org/10.48550/arXiv.2206.06686

    work page doi:10.48550/arxiv.2206.06686 2023

  39. [39]

    Joaquin Vanschoren, Jan N

    Thanasilp, S., Wang, S., Cerezo, M., Holmes, Z.: Exponential concentration in quantum kernel methods. Nature Communications15(1), 5200 (2024) https:// doi.org/10.1038/s41467-024-49287-w

    work page doi:10.1038/s41467-024-49287-w 2024

  40. [40]

    Acero, Z

    Javadi-Abhari, A., Treinish, M., Krsulich, K., Wood, C.J., Lishman, J., Gacon, J., Martiel, S., Nation, P.D., Bishop, L.S., Cross, A.W., Johnson, B.R., Gambetta, J.M.: Quantum computing with Qiskit (2024). https://doi.org/10.48550/arXiv. 2405.08810 20

    work page internal anchor Pith review doi:10.48550/arxiv 2024

  41. [41]

    Patrick Rebentrost, Masoud Mohseni, and Seth Lloyd

    Peters, E., Caldeira, J., Ho, A., Leichenauer, S., Mohseni, M., Neven, H., Spent- zouris, P., Strain, D., Perdue, G.N.: Machine learning of high dimensional data on a noisy quantum processor. npj Quantum Information7(1), 161 (2021) https://doi.org/10.1038/s41534-021-00498-9

    work page doi:10.1038/s41534-021-00498-9 2021

  42. [42]

    Machine Learning: Science and Technology 4(1), 015005 (2023) https://doi.org/10.1088/2632-2153/acb0b4

    Haug, T., Self, C.N., Kim, M.S.: Quantum machine learning of large datasets using randomized measurements. Machine Learning: Science and Technology 4(1), 015005 (2023) https://doi.org/10.1088/2632-2153/acb0b4

    work page doi:10.1088/2632-2153/acb0b4 2023

  43. [43]

    Quantum Machine Intelligence3(1), 9 (2021) https://doi.org/10.1007/s42484-021-00038-w

    Hubregtsen, T., Pichlmeier, J., Stecher, P., Bertels, K.: Evaluation of parameter- ized quantum circuits: on the relation between classification accuracy, express- ibility, and entangling capability. Quantum Machine Intelligence3(1), 9 (2021) https://doi.org/10.1007/s42484-021-00038-w

    work page doi:10.1007/s42484-021-00038-w 2021

  44. [44]

    Quantum8, 1385 (2024) https://doi.org/10.22331/q-2024-06-25-1385

    Kreplin, D.A., Roth, M.: Reduction of finite sampling noise in quantum neural networks. Quantum8, 1385 (2024) https://doi.org/10.22331/q-2024-06-25-1385

    work page doi:10.22331/q-2024-06-25-1385 2024

  45. [45]

    IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)31(4), 629–636 (2001) https://doi.org/10

    Malina, W.: Two-parameter fisher criterion. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)31(4), 629–636 (2001) https://doi.org/10. 1109/3477.938265

    work page arXiv 2001

  46. [46]

    In: Pattern Recognition and Image Analysis, pp

    Mollineda, R.A., S´ anchez, J.S., Sotoca, J.M.: Data characterization for effec- tive prototype selection. In: Pattern Recognition and Image Analysis, pp. 27–34. Springer, Berlin, Heidelberg (2005). https://doi.org/10.1007/11492542 4

    work page doi:10.1007/11492542 2005

  47. [47]

    IEEE Transac- tions on ComputersC-17(4), 367–372 (1968) https://doi.org/10.1109/TC.1968

    Smith, F.W.: Pattern classifier design by linear programming. IEEE Transac- tions on ComputersC-17(4), 367–372 (1968) https://doi.org/10.1109/TC.1968. 229395

    work page doi:10.1109/tc.1968 1968

  48. [48]

    In: Pattern Recognition, International Conference On, vol

    Hoekstra, A., Duin, R.P.W.: On the Nonlinearity of Pattern Classifiers . In: Pattern Recognition, International Conference On, vol. 4, p. 271. IEEE Com- puter Society, Los Alamitos, CA, USA (1996). https://doi.org/10.1109/ICPR. 1996.547429

    work page doi:10.1109/icpr 1996

  49. [49]

    IEEE Transactions on Knowledge and Data Engineering36(7), 3580–3599 (2024)

    Leyva, E., Gonz´ alez, A., P´ erez, R.: A set of complexity measures designed for applying meta-learning to instance selection. IEEE Transactions on Knowledge and Data Engineering27(2), 354–367 (2015) https://doi.org/10.1109/TKDE. 2014.2327034

    work page doi:10.1109/tkde 2015

  50. [50]

    Neurocomput- ing75(1), 33–42 (2012) https://doi.org/10.1016/j.neucom.2011.03.054

    Lorena, A.C., Costa, I.G., Spolaˆ or, N., de Souto, M.C.P.: Analysis of complexity indices for classification problems: Cancer gene expression data. Neurocomput- ing75(1), 33–42 (2012) https://doi.org/10.1016/j.neucom.2011.03.054 . Brazilian Symposium on Neural Networks (SBRN 2010) International Conference on Hybrid Artificial Intelligence Systems (HAIS 2010)

    work page doi:10.1016/j.neucom.2011.03.054 2012

  51. [51]

    classification accuracy: A comprehensive study of evolutionary algorithms with biomedical datasets

    Tanwani, A.K., Farooq, M.: Classification potential vs. classification accuracy: A comprehensive study of evolutionary algorithms with biomedical datasets. In: 21 Learning Classifier Systems, pp. 127–144. Springer, Berlin, Heidelberg (2010). https://doi.org/10.1007/978-3-642-17508-4 9 22

    work page doi:10.1007/978-3-642-17508-4 2010