Exponential concentration in quantum kernel methods

arXiv:2208.11060v2 Announce Type: replace-cross
Abstract: Kernel methods in Quantum Machine Learning (QML) have recently gained significant attention as a potential candidate for achieving a quantum advantage in data analysis. Among other attractive properties, when training a kernel-based model one is guaranteed to find the optimal model's parameters due to the convexity of the training landscape. However, this is based on the assumption that the quantum kernel can be efficiently obtained from quantum hardware. In this work we study the performance …

abstract analysis arxiv attention cs.lg data data analysis kernel machine machine learning parameters qml quant-ph quantum quantum advantage stat.ml training type