Expressivity of IQP Feature-Map Quantum Kernels via Reproducing Kernel Hilbert Spaces
Read the original on arXiv Machine Learning →The paper studies the expressivity of Instantaneous Quantum Polynomial (IQP) feature‑map quantum kernels by deriving a Fourier representation of their associated Reproducing Kernel Hilbert Space (RKHS). It identifies three bandwidth regimes—localized, multimodal, and periodic—each with distinct expressive properties, and demonstrates these regimes on synthetic datasets for classification and anomaly detection, comparing against a classical Gaussian kernel. The work provides a clear link between the kernel’s accessible frequencies, its bandwidth hyperparameter, and the structure of the data, offering guidance for bandwidth selection when data exhibit known periodic or multimodal patterns.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.