The Impact of Feature Embedding Placement in the Ansatz of a Quantum Kernel in QSVMs
This work addresses a critical but underexplored issue in quantum machine learning for researchers aiming to optimize quantum kernels, though it appears incremental as it builds on and refines existing architectures.
The paper tackled the problem of designing feature maps for quantum kernels in Quantum Support Vector Machines (QSVMs), specifically focusing on how feature-dependent gates are placed in circuit architectures, and found that existing styles do not perform as expected, with a novel alternative achieving similar performance using fewer gates.
Designing a useful feature map for a quantum kernel is a critical task when attempting to achieve an advantage over classical machine learning models. The choice of circuit architecture, i.e. how feature-dependent gates should be interwoven with other gates is a relatively unexplored problem and becomes very important when using a model of quantum kernels called Quantum Embedding Kernels (QEK). We study and categorize various architectural patterns in QEKs and show that existing architectural styles do not behave as the literature supposes. We also produce a novel alternative architecture based on the old ones and show that it performs equally well while containing fewer gates than its older counterparts.