Improving quantum classifier performance in nisq computers by voting strategy from ensemble learning

This study addresses the significant hurdle of quantum noise in Noisy Intermediate-Scale Quantum (NISQ) computers, which jeopardizes the performance of variational quantum classifiers (VQCs) for image classification. Previous studies have explored using ensemble learning in conventional computing to reduce quantum noise. However, the authors point out that the simple average aggregation in classical ensemble learning may not work well for NISQ computers due to the unbalanced confidence distribution in VQCs. Therefore, they suggest optimizing ensemble quantum classifiers with plurality voting. Experiments conducted on the MNIST dataset and IBM quantum computers show that the proposed method can outperform state-of-the-art on two- and four-class classifications by up to 16.0% and 6.1%, respectively. PDF