Compositional optimization of quantum circuits for quantum kernels of support vector machines
This work addresses the problem of improving quantum machine learning for classification tasks, but it appears incremental as it builds on existing quantum kernel methods with a Bayesian optimization approach.
The authors tackled the challenge of building quantum machine learning models that outperform classical ones by developing a Bayesian algorithm to adapt quantum gate sequences for support vector machine kernels, resulting in quantum models that significantly exceed the performance of optimized classical models with conventional kernels.
While quantum machine learning (ML) has been proposed to be one of the most promising applications of quantum computing, how to build quantum ML models that outperform classical ML remains a major open question. Here, we demonstrate a Bayesian algorithm for constructing quantum kernels for support vector machines that adapts quantum gate sequences to data. The algorithm increases the complexity of quantum circuits incrementally by appending quantum gates selected with Bayesian information criterion as circuit selection metric and Bayesian optimization of the parameters of the locally optimal quantum circuits identified. The goal is to build quantum kernels for SVM that can solve classification problems with as little training data as possible. The performance of the resulting quantum models for the classification problems considered here significantly exceeds that of optimized classical models with conventional kernels.