The Cross-Kernel Margin: A Robustness Measure for Quantum Kernel Methods

Abstract

Quantum devices in the current Noisy Intermediate-Scale Quantum (NISQ) era are inherently affected by noise, which can degrade the predictive performance of quantum machine learning models. In this work, we introduce a new margin-based robustness measure for Quantum Kernel-Assisted Support Vector Machines (QSVMs), termed the cross-kernel margin. This measure quantifies the stability of a classifier learned under a perturbed kernel relative to the ideal feature space. We derive a posteriori stability bounds for the corresponding cross-kernel inverse squared-margin under kernel perturbations using the Tikhonov-stabilised SVM dual formulation. The local depolarising noise model is then applied to this framework to induce perturbations in the kernel. The resulting bounds are numerically checked using simulations across multiple datasets and further tested using kernel matrices obtained from real quantum hardware and a noisy backend simulator. Furthermore, we empirically compare the degradation of test accuracy under local depolarising noise with the commonly used global depolarising noise model in order to motivate its use in our study. Finally, we present empirical results linking margin-based quantities with the generalisation performance of QSVMs, providing additional motivation for our margin-based robustness analysis.

34 pages, 12 figures; substantially rewritten, new bound independent of noise model; mathematically stronger result; reframed as a robustness study