Efficient Discrete Feature Encoding for Variational Quantum Classifier

Recent days have witnessed significant interests in applying quantum-enhanced techniques for solving a variety of machine learning tasks. Variational methods that use quantum resources imperfect devices with the help classical computing are popular supervised learning. classification (VQC) is one such possible advantage using features hard to compute by methods. Its performance depends on mapping into feature space. Although there been many quantum-mapping functions proposed so far, little discussion efficient discrete features, as age group, zip code, and others, which often classifying datasets interest. We first introduce random-access coding (QRAC) map efficiently limited number qubits VQC. In numerical simulations, we present range encoding strategies demonstrate their limitations capabilities. experimentally show QRAC can speeding up training VQC reducing its parameters via saving mapping. confirm effectiveness experimenting real-world both simulators real devices.