Quantum kernel methods utilize high-dimensional quantum feature spaces as a theoretically motivated strategy to address data scarcity in supervised classification. However, theoretical analyses predict exponential concentration of quantum kernel similarity values as qubit count increases. This study presents the first statistically controlled empirical evaluation of fixed-feature-map quantum support vector machines (QSVMs) for few-shot keyword spotting. The ZZFeatureMap and PauliFeatureMap circuits (2 to 3 qubits, PCA-compressed MFCC features, ~51% variance retained) were evaluated across 24 configurations and four low-resource regimes (5–30 samples per class) on the Google Speech Commands dataset, using ten independent seeds with Wilcoxon signed-rank tests and Bonferroni correction. Across all configurations and sample sizes, QSVM accuracy remained close to the five-class random baseline (19.3% at 30 samples per class; random baseline 20%), while RBF SVM achieved 38.7% and a compact CNN achieved 65.3%. Direct kernel similarity measurement confirmed severe concentration, where the 3-qubit QSVM produced near-identical same-class and different-class similarity means (both approximately 0.192), with 94.1% overlap. Under matched MFCC+PCA features, all classical kernels outperformed QSVM, including linear SVM (Cliff’s $\delta = -0.98$ , $p = 0.002$ ) and RBF SVM ( $\delta = -0.82$ , $p = 0.002$ , Bonferroni-corrected $\alpha = 0.003$ ), with CNN achieving complete stochastic dominance ( $\delta = -1.00$ ). These results empirically validate quantum kernel concentration in structured acoustic classification within evaluated NISQ constraints, and apply specifically to the fixed-feature-map paradigm, not quantum kernel methods in general. The identified failure modes, namely exponential concentration, geometric misalignment, and limited circuit expressivity, provide concrete directions for future research into trainable quantum feature maps and hybrid quantum-classical architectures.
Quantum kernel methods utilize high-dimensional quantum feature spaces as a theoretically motivated strategy to address data scarcity in supervised classification. However, theoretical analyses predict exponential concentration of quantum kernel similarity values as qubit count increases. This study presents the first statistically controlled empirical evaluation of fixed-feature-map quantum support vector machines (QSVMs) for few-shot keyword spotting. The ZZFeatureMap and PauliFeatureMap circuits (2 to 3 qubits, PCA-compressed MFCC features, ~51% variance retained) were evaluated across 24 configurations and four low-resource regimes (5–30 samples per class) on the Google Speech Commands dataset, using ten independent seeds with Wilcoxon signed-rank tests and Bonferroni correction. Across all configurations and sample sizes, QSVM accuracy remained close to the five-class random baseline (19.3% at 30 samples per class; random baseline 20%), while RBF SVM achieved 38.7% and a compact CNN achieved 65.3%. Direct kernel similarity measurement confirmed severe concentration, where the 3-qubit QSVM produced near-identical same-class and different-class similarity means (both approximately 0.192), with 94.1% overlap. Under matched MFCC+PCA features, all classical kernels outperformed QSVM, including linear SVM (Cliff’s δ=−0.98 , p=0.002 ) and RBF SVM ( δ=−0.82 , p=0.002 , Bonferroni-corrected α=0.003 ), with CNN achieving complete stochastic dominance ( δ=−1.00 ). These results empirically validate quantum kernel concentration in structured acoustic classification within evaluated NISQ constraints, and apply specifically to the fixed-feature-map paradigm, not quantum kernel methods in general. The identified failure modes, namely exponential concentration, geometric misalignment, and limited circuit expressivity, provide concrete directions for future research into trainable quantum feature maps and hybrid quantum-classical architectures.
This thesis presents a systematic empirical evaluation of quantum machine learning performance under noisy intermediate-scale quantum (NISQ) era constraints. Through 670 controlled experiments, it evaluated quantum kernel support vector machines and variational quantum classifiers against classical baselines on MNIST binary and multiclass classification tasks with systematic variation of problem difficulty, feature dimensionality (4, 8 qubits), and training set size (n ∈{100, 250, 400, 500, 2000, 4000}). Statistical rigor was ensured through five random seeds per condition and comprehensive significance testing. During the testing with binary datasets, classical methods (SVM, logistic regression, k-NN, neural networks) achieved 85.9% to 99.6% accuracy with training times under one second across all sample sizes. Quantum kernel methods utilizing ZZ feature maps yielded 70.5% to 96.0% accuracy, requiring 129 to 2,140 seconds training with quadratic sample size scaling. Larger scale quantum experiments (n = 4000 for both architectures, 8-qubit encoding with n = 2000 for quantum kernels) proved computationally impossible on available hardware leading to out of memory errors, highlighting practical NISQ-era scalability constraints. Variational quantum classifiers exhibited persistent performance stagnation, failing to exceed 66.5% accuracy despite increases in training data and feature dimensionality. Performance gaps ranged from 3.3 to 35.2 percentage points. All quantum classical differences achieved statistical significance (p< 0.05, with 13 of 14 comparisons meeting p< 0.01) and exhibited large to very large efect sizes (d> 1.0, with 13 of 14 comparisons exceeding d> 2.0). To further evaluate performance and scalability, a 4 class classification experiment was conducted following an identical experimental protocol, with training set sizes of n ∈{100, 250, 400}. Across 180 runs, classical baselines achieved mean accuracies between 87.2% and 95% across both 4 and 8 dimensional data. Quantum Kernel SVM struggled during runs with 4 dimensions, accuracy varying between 64.6% and 74%. Quantum Kernel SVM accuracy declined 16%-25% when the dimension and qubit count were increased to 8, showing findings of exponential kernel concentration. The Variational Quantum Classifier also performed poorly, with accuracy ranging from 43.4% to 44.6% across all runs, providing further evidence that it failed to leverage additional features or training data. Experiments employed noiseless statevector simulation, establishing that quantum underperformance stems from fundamental algorithmic limitations independent of hardware noise. A further extension to 8 class classification (digits 0–7) confirmed and amplified these findings: classical methods maintained 65–83% accuracy while Quantum Kernel SVM degraded to 34–47% and VQC collapsed to 21–23%, approaching the 12.5% random baseline. Supplementary appendix experiments further examined amplitude encoding on raw 784 dimensional pixel features and an alternative angle encoding scheme on the 8-class task; the latter demonstrated that replacing the ZZ Feature Map with simple per qubit rotations substantially recovered quantum kernel performance, suggesting feature map design as a more consequential variable than circuit depth or qubit count in near-term quantum classification.
Quantum kernel methods have been proposed as a promising approach for leveraging near-term quantum computers for supervised learning, yet rigorous benchmarks against strong classical baselines remain scarce. We present a comprehensive empirical study of quantum kernel support vector machines (QSVMs) across nine binary classification datasets, four quantum feature maps, three classical kernels, and multiple noise models, totalling 970 experiments with strict nested cross-validation.
Our analysis spans four phases: (i) statistical significance testing, revealing that none of 29 pairwise quantum-classical comparisons reach significance at α=0.05; (ii) learning curve analysis over six training fractions, showing steeper quantum slopes on six of eight datasets that nonetheless fail to close the gap to the best classical baseline; (iii) hardware validation on IBM ibm_fez (Heron r2), demonstrating kernel fidelity r≥0.976 across six experiments; and (iv) seed sensitivity analysis confirming reproducibility (mean CV 1.4%).
A Kruskal-Wallis factorial analysis reveals that dataset choice dominates performance variance (ε2=0.73), while kernel type accounts for only 9%. Spectral analysis offers a mechanistic explanation: current quantum feature maps produce eigenspectra that are either too flat or too concentrated, missing the intermediate profile of the best classical kernel, the radial basis function (RBF). Quantum kernel training (QKT) via kernel-target alignment yields the single competitive result -- balanced accuracy 0.968 on breast cancer -- but with ~2,000x computational overhead.
Our findings provide actionable guidelines for quantum kernel research. The complete benchmark suite is publicly available to facilitate reproduction and extension.
Reproducibility archive (code + manuscript) for the paper "Benchmarking Quantum Kernel Support Vector Machines Against Classical Baselines on Tabular Data: A Rigorous Empirical Study with Hardware Validation" (arXiv:2604.18837). The archive contains the full Python benchmark framework, experiment configurations, unit tests, and the compiled manuscript. Quantum kernel methods have been proposed as a promising approach for leveraging near-term quantum computers for supervised learning, yet rigorous benchmarks against strong classical baselines remain scarce. We present a comprehensive empirical study of quantum kernel support vector machines (QSVMs) across nine binary classification datasets, four quantum feature maps, three classical kernels, and multiple noise models, totalling 970 experiments with strict nested cross-validation. Our analysis spans four phases: (i) statistical significance testing; (ii) learning curve analysis; (iii) hardware validation on IBM ibm_fez (Heron r2); and (iv) seed sensitivity analysis. A Kruskal–Wallis factorial analysis reveals that dataset choice dominates performance variance (ε2=0.73), while kernel type accounts for only 9%. Spectral analysis offers a mechanistic explanation: current quantum feature maps produce eigenspectra that are either too flat or too concentrated, missing the intermediate profile of the best classical kernel (RBF). The complete benchmark suite is publicly available to facilitate reproduction and extension.
Quantum kernel methods are often proposed as a route to improved medical image classification because quantum feature maps can embed data into high-dimensional Hilbert spaces. However, their practical value remains unclear when compared with strong classical kernels under leakage-controlled conditions. This study benchmarks two simulated quantum kernel support vector machines, QSVM-ZZ and QSVM-Pauli, against logistic regression, linear SVM, fixed-default RBF-SVM, and a compact multi-layer perceptron on BrainTumorMRI and BreastMNIST. All models used identical frozen ResNet18 features, train-only standardisation, PCA compression to four and eight dimensions, three random seeds, and matched classifier-training budgets where applicable. Across 24 seed-level matched comparisons, the best quantum kernel model never outperformed the best classical model. The mean quantum-minus-classical macro-F1 gap was - 0.2230, with all 24 gaps negative. Fixed pairwise comparisons confirmed that RBF-SVM exceeded both quantum kernels individually. QSVMs also required approximately 50 × to more than 220 × higher runtime. These findings show that, for compressed ResNet18 medical image features under noiseless simulation, the tested QSVM-ZZ and QSVM-Pauli kernels did not provide a practical advantage over fixed-default RBF-SVM.
Abstract This work presents an empirical study of a Quantum Support Vector Machine(QSVM) for classification of radar micro-Doppler signatures, used here as astructured benchmark for evaluating quantum kernel methods under realistichardware constraints. Extracted classical features are reduced using PrincipalComponent Analysis (PCA) to enable compact quantum encoding, and mappedinto a quantum kernel feature space through a fully entangling ZZFeatureMap.Classification is performed using a kernel-based QSVM and compared with aclassical SVM baseline under consistent preprocessing and evaluation conditions.Performance is assessed in both ideal simulation and on NISQ-era superconducting quantum processors, specifically IBM Torino (133-qubit) and IBM Fez(156-qubit). Results show that the QSVM attains competitive accuracy whileoperating on reduced feature dimensionality, with performance sensitivity tonoise, decoherence, and measurement shot count. Improved kernel stability isobserved on newer hardware architecture.The study does not claim quantumadvantage; instead, it provides a hardware-level evaluation of quantum kernelbehavior and clarifies current feasibility and limitations of QSVM approaches forstructured signal classification tasks.
Quantum machine learning on near-term noisy quantum devices has generated substantial theoretical interest, but rigorous empirical comparisons under realistic noise on practically relevant data remain scarce. This paper compares two paradigmatic quantum learning models, a Quantum Support Vector Machine (QSVM) built on the ZZFeatureMap quantum kernel and a Variational Quantum Classifier (VQC) with an EfficientSU2/RealAmplitudes ansatz, against tuned classical baselines (SVM with four kernels, Random Forest, XGBoost, LightGBM and CatBoost) on the ULB Credit Card Fraud dataset (284,807 transactions, 0.17% fraud). All models share an identical 4-qubit PCA-reduced feature space, evaluated on the full unbalanced test fold over 15 fits (3 folds × 5 seeds) and reported as mean ± standard deviation with bootstrap confidence intervals, AUPRC as the primary metric. Noise robustness is assessed under depolarizing noise p∈{0,0.001,0.01,0.05}, with ranking preservation measured directly through Spearman ρ and Kendall τ between the noisy and noiseless decision scores rather than read off AUPRC, alongside the per-paradigm computational cost. At four qubits the classical baselines lead (AUPRC 0.60 to 0.74, CatBoost best), above the VQC (0.494) and the QSVM (0.240); the controlled QSVM-versus-RBF–SVM comparison puts the cost of the quantum kernel at about 0.45 AUPRC. Under noise the QSVM keeps its score ranking (ρ=0.998 at p=0.001, 0.906 at p=0.01) and an operational decision threshold (recall 0.87 to 0.89, stable calibration), while the VQC AUPRC peaks non-monotonically at p=0.01 (0.494 rising to 0.654, then easing to 0.569 at p=0.05) even as its ranking decays monotonically (ρ from 0.72 to near zero), so average precision on its own misrepresents how noise affects it. The quantum models do not surpass the tuned classical reference at four qubits; the contribution is methodological: under noise, AUPRC has to be read together with a genuine rank statistic, because the two can move in opposite directions.