Efficient Implementation of the Vector-Valued Kernel Ridge Regression for the Uncertainty Quantification of the Scattering Parameters of a 2-GHz Low-Noise Amplifier

This paper focuses on the application of an efficient implementation of the vector-valued kernel Ridge regression (KRR) to the uncertainty quantification (UQ) of the scattering parameters of a low-noise amplifier (LNA). Specifically, the performance of the proposed technique have been investigated for the statistical assessment of the mean value, variance and probability density function (PDF) of the S11 and S21 parameters of a 2-GHz LNA induced by 25 stochastic input parameters and compared with the corresponding reference results computed via a plain Monte Carlo (MC) simulation.