Performance Analysis of Quantum Support Vector Classifiers and Quantum Neural Networks

TL;DR

This paper compares quantum and classical machine learning models, showing quantum models outperform classical ones on complex tasks, with insights into hyperparameter tuning and framework efficiency.

Contribution

It provides a comparative analysis of QSVCs and QNNs on benchmark datasets, highlighting their performance, hyperparameter effects, and implementation frameworks.

Findings

Quantum models outperform classical models on complex tasks.

Qiskit framework offers better optimization than PennyLane.

Hyperparameters significantly influence quantum model accuracy.

Abstract

This study explores the performance of Quantum Support Vector Classifiers (QSVCs) and Quantum Neural Networks (QNNs) in comparison to classical models for machine learning tasks. By evaluating these models on the Iris and MNIST-PCA datasets, we find that quantum models tend to outperform classical approaches as the problem complexity increases. While QSVCs generally provide more consistent results, QNNs exhibit superior performance in higher-complexity tasks due to their increased quantum load. Additionally, we analyze the impact of hyperparameter tuning, showing that feature maps and ansatz configurations significantly influence model accuracy. We also compare the PennyLane and Qiskit frameworks, concluding that Qiskit provides better optimization and efficiency for our implementation. These findings highlight the potential of Quantum Machine Learning (QML) for complex classification problems and provide insights into model selection and optimization strategies