Hyper-parameter Tuning for Quantum Support Vector Machine

In recent years, the positive effect of quantum techniques on machine learning methods have been studied. Especially in training big data, quantum computing is beneficial in terms of speed. This study examined and applied the Quantum Support Vector Machine steps to the breast cancer dataset. Different types of feature maps used in the conversion of a classical dataset to a quantum dataset were examined using different dimensions. One of the factors that directly affect the performance of machine learning models is the correct selection of the hyper-parameters. These values must be obtained independent from the designer. Within the scope of the study, the hyper-parameter tuning methods, namely, Grid, Random, and Bayesian search methods, were examined. By using these methods, the hyper-parameters of the Support vector machine, which is one of the machine learning methods, were found. The performances of Linear, Non-linear and Quantum support vector machines were compared, and the running costs were analyzed.

Automated summary

In recent years, the positive effect of quantum techniques on machine learning methods, especially in dealing with big data, has been studied. This study applied Quantum Support Vector Machine steps to the breast cancer dataset, examined different feature maps and hyper-parameter tuning methods, and compared the performances and running costs of Linear, Non-linear, and Quantum support vector machines.