Reliable pulsar candidate ranking requires probability estimates that are not only discriminative but also well calibrated. We evaluate hybrid quantum-calssical logistic regression on the imbalanced HTRU-2 dataset using three quantum feature encodings: angle encoding, amplitude encoding, and data re-uploading. The models are trained using analytic gradients and compared with classical baselines and a quantum support vector machine reference model under a paired-seed protocol. Evaluation combines rare-event discrimination, low-false-positive-rate recovery, probability calibration, and runtime analysis. Angle encoding gives the strongest performance among the quantum logistic regression variants. At shallow depth, the angle-encoded model remains close to the best classical baselines in discrimination and low-false-positive-rate recovery, while also giving the lowest calibration error at the benchmark configuration. Murphy decomposition shows that the angle-encoded model maintains low reliability error and high, stable resolution across circuit depths and training-set sizes. This means that its probability estimates preserve both calibration and meaningful separation between candidate groups. Data re-uploading is competitive at small depth but loses discrimination and resolution at larger depth in the present multi-qubit implementation, while amplitude encoding remains weaker across dataset sizes. Shallow angle-encoded quantum logistic regression therefore gives the best balance among the tested quantum logistic models, although simulation runtime remains a practical limitation.
Reliable pulsar candidate ranking requires probability estimates that are not only discriminative but also well calibrated. We evaluate hybrid quantum-calssical logistic regression on the imbalanced HTRU-2 dataset using three quantum feature encodings: angle encoding, amplitude encoding, and data re-uploading. The models are trained using analytic gradients and compared with classical baselines and a quantum support vector machine reference model under a paired-seed protocol. Evaluation combines rare-event discrimination, low-false-positive-rate recovery, probability calibration, and runtime analysis. Angle encoding gives the strongest performance among the quantum logistic regression variants. At shallow depth, the angle-encoded model remains close to the best classical baselines in discrimination and low-false-positive-rate recovery, while also giving the lowest calibration error at the benchmark configuration. Murphy decomposition shows that the angle-encoded model maintains low reliability error and high, stable resolution across circuit depths and training-set sizes. This means that its probability estimates preserve both calibration and meaningful separation between candidate groups. Data re-uploading is competitive at small depth but loses discrimination and resolution at larger depth in the present multi-qubit implementation, while amplitude encoding remains weaker across dataset sizes. Shallow angle-encoded quantum logistic regression therefore gives the best balance among the tested quantum logistic models, although simulation runtime remains a practical limitation.
This paper presents a hybrid quantum logistic regression model for binary data classification that combines classical logistic regression methods with quantum computing to improve efficiency and speed up the learning process. Quantum computing is used to represent and process feature and weight vectors as quantum states and to efficiently compute the dot product underlying the logistic function. The use of normalized amplitude coding allows for compact representation of feature vectors and weights, reducing the number of qubits required and potentially speeding up computations for high-dimensional classification problems where classical methods may encounter scalability limitations. The quantum dot product computation is performed using the Hadamard test, which provides a statistical estimate of the probability of measuring an auxiliary qubit. The auxiliary qubit is first put into a superposition state, and after performing controlled unitary operations, amplitude interference is formed, which depends on the scalar product of the feature vector and weight coefficients. The obtained measurement probability is used to estimate the scalar product of the feature vectors and weights. The classical part of the model provides for the execution of operations that are difficult to implement on modern quantum devices, in particular, vector normalization, application of the sigmoid function to estimate the probability of an object belonging to a certain class, calculation of the loss function and iterative update of weight coefficients by the gradient descent method. The purpose of classification is to predict the binary class for an unknown sample based on the training sample. To demonstrate the model, a numerical example is given with a step-by-step calculation of one iteration of logistic regression training. In addition, computer modeling of the hybrid algorithm training process was performed, taking into account the influence of noise on the results of quantum state measurements. A quantum noise model was developed based on the probability of confidence in the measurement result, which is interpreted as an assessment of its reliability in a Bernoulli experiment. Comparison of the obtained results with the classical approach confirms the practical suitability of the hybrid algorithm for binary classification problems. The hybrid model preserves the key properties of classical logistic regression – parameter interpretability and optimization stability, while allowing for the use of quantum advantages for compact data encoding and scalar product computation. This makes the study of hybrid logistic regression relevant for the development of machine learning algorithms on modern quantum platforms.
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.
Financial fraud detection remains difficult due to extreme class imbalance and subtle, nonlinear patterns in transactional data. We investigate a hybrid quantum–classical approach that couples a fidelity-based quantum kernel with a logistic regression classifier (QEKLR). A custom ZZ-inspired feature map comprising Hadamards, mixed-axis Ry/Rzencodings, tunable Ising-ZZ cross terms, and data re-uploading, embeds PCA-reduced, Min–Max scaled features into quantum states. The resulting fidelity kernel is evaluated and used within kernel logistic regression. Experiments on two benchmarks: BankSim (synthetic) and the European Credit Card Fraud dataset, use balanced subsets created via Random Under-Sampling. The proposed model attains the best performance on BankSim (AUC = 0.96; strongest F1), and is competitive on the credit-card dataset (AUC = 0.94), closely tracking XGBoost (AUC = 0.96) while outperforming logistic regression and a variational quantum classifier baseline. These results indicate that quantum kernel methods can provide practical gains on tabular fraud tasks while remaining aligned with current NISQ constraints. We also discuss the quadratic cost of exact kernel evaluation and outline scalable approximations for future deployment on larger, highly imbalanced datasets.
Quantum Support Vector Machines (QSVMs) are frequently reported to outperform classical kernels on high-dimensional gene expression data, but such comparisons are sensitive to how the evaluation is constructed. This study compares a fidelity-based quantum kernel against six classical baselines — linear and RBF SVMs, random forest, gradient boosting, a multilayer perceptron and logistic regression — on two public breast cancer cohorts, GSE2034 (286 samples) and GSE2990 (125 samples), each described by 22,283 probes. Every preprocessing step, including imputation, gene selection, feature scaling and class rebalancing, is fitted within the training fold of a repeated stratified five-fold cross-validation, and comparisons are tested with a corrected paired t-test that accounts for the dependence between folds. Under this protocol the quantum kernel is statistically indistinguishable from every classical baseline in all four experimental conditions: no comparison reaches significance after correction, and the largest ROC-AUC gap to the strongest baseline is 0.036 (95% CI −0.073 to 0.002). Two implementation factors are shown to dominate the outcome. First, rebalancing or scaling before the train–test split inflates apparent quantum performance, because duplicated minority samples appear on both sides of the split. Second, encoding standardised expression values directly as rotation angles causes kernel concentration, which drives QSVM ROC-AUC to chance (0.501) on GSE2034; restricting the encoding to [0, π/2] restores discriminative performance. Probes selected by a supervised within-fold filter and ranked by permutation importance under the quantum kernel recover known breast cancer markers, including CD44 on GSE2034 and MMP10 on GSE2990. We conclude that reported quantum-kernel advantages on these cohorts are attributable to evaluation protocol and encoding choices rather than to the quantum kernel itself, and we provide the diagnostic used to detect kernel concentration.
Comparisons of quantum data-encoding strategies are rarely accompanied by a registered estimand, an explicit treatment of where simulated noise is applied, or a classical reference point. This study reports a registered simulation study of the interaction between data encoding (angle versus ZZ feature map) and circuit noise (noiseless versus single-Pauli errors with probability p = 0.02 after every CNOT, plus readout flips) for an 8-qubit variational quantum classifier trained with SPSA. Three binary datasets, ten confirmatory seeds (240 runs) and circuit size as a secondary factor were used. Hyperparameters were tuned symmetrically on separate seeds and frozen before the confirmatory runs. The registered primary estimand, the Encoding x Noise interaction on validation balanced accuracy, was -0.154 (95% seed-cluster bootstrap CI [-0.181, -0.124]), which supports the registered directional hypothesis. ZZ-encoded models trained under noise met the pre-declared convergence criterion in 1 of 60 runs, against 48 of 60 for angle encoding, so training failure and signal degradation are not separated by the registered design. An exploratory follow-up, in which ZZ models were trained without noise and evaluated under noise, showed accuracy falling to 0.55-0.63 at p = 0.02, which points to the number of noisy two-qubit gates (56 additional CNOTs) as the main driver. The registered transfer hypothesis was not supported: robust selection did not differ from naive selection (+0.003, CI [-0.012, +0.016]). A class-balanced logistic regression exceeded every quantum configuration on validation accuracy. No quantum advantage is claimed.
Variational quantum classifiers (VQCs) are often compared with classical models under unequal data partitions, tuning budgets, or statistical treatment. We benchmark a 4-qubit VQC against logistic regression, an RBF-SVM, random forest, a quantum-kernel SVM (QSVM), and a majority-class control on Breast Cancer Wisconsin (n=569), Coimbra (n=116), and Golub leukemia (n=72), using five stratified folds across five seeds (25 paired blocks per dataset), identical training-fold-fitted preprocessing, and Nadeau–Bengio corrected paired tests with Holm correction. A first arm with a frozen configuration and the common [0, π] angle encoding left the VQC at 0.563, 0.515, and 0.576 accuracy (majority 0.617, 0.552, 0.652). In a second arm, in which every model was tuned by the same inner cross-validation and the encoding scale was a tuned hyperparameter, VQC accuracy rose to 0.864, 0.616, and 0.747. On Wisconsin the VQC stayed significantly below every matched classical model (differences 0.079–0.097, Holm p≤0.006) but above the majority class; on Golub it was significantly below only the SVM (Holm p=0.016); on Coimbra no comparison was significant. A QSVM with the same feature map exceeded the VQC numerically on every dataset, and three optimizers reached the same training loss in pilot diagnostics, pointing to the encoding and the variational head rather than the optimizer. The Wisconsin arms also differ in sample size (120 versus 569). Results apply to this low-qubit, PCA-compressed, exactly simulated setting and do not indicate a quantum advantage.