Empowering complex-valued data classification with the variational quantum classifier

Abstract

The evolution of quantum computers has encouraged research into how to handle tasks with significant computation demands in the past few years. Due to the unique advantages of quantum parallelism and entanglement, various types of quantum machine learning (QML) methods, especially variational quantum classifiers (VQCs), have attracted the attention of many researchers and have been developed and evaluated in numerous scenarios. Nevertheless, most of the research on VQCs is still in its early stages. For instance, as a consequence of the mathematical constraints imposed by the properties of quantum states, the majority of research has not fully taken into account the impact of data formats on the performance of VQCs. In this paper, considering a significant number of data in the real world exist in the form of complex numbers, i.e., phasor data in power systems and the result of Fourier transform on image processing, we develop two categories of data encoding methods, including coupling data encoding and splitting data encoding. This paper features the coupling data encoding method to encode complex-valued data in a way of amplitude encoding. By leveraging the property of quantum states living in a complex Hilbert space, the complex-valued data is embedded into the amplitude of quantum states to comprehensively characterize complex-valued information. Optimizers will be utilized to iteratively tune a parameterized ansatz, with the aim of minimizing the value of loss functions defined with respect to the specific classification task. In addition, distinct factors in VQCs have been explored in detail to investigate the performance of VQCs, including data encoding methods, loss functions, and optimizers. The experimental result shows that the proposed data encoding method outperforms other typical encoding methods on a given classification task. Moreover, different loss functions are tested, and the capability of finding the minimum value is evaluated for gradient-free and gradient-based optimizers, which provides valuable insights and guidelines for practical implementations.