On spectral windows in supervised learning from data

For Tikhonov regularization in supervised learning from data, the effect on the regularized solution of a joint perturbation of the regression function and the data is investigated. Spectral windows in the finite-sample and population cases are compared via probabilistic estimates of the differences between regularized solutions.

Research highlights
► Spectral windows allow one to investigate the robustness of supervised learning, algorithms based on Tikhonov regularization.
► Probabilistic estimates can be derived for supervised learning in the presence of both noisy data and perturbations in the regression function.
► Spectral windows in the finite-sample and population cases are compared via probabilistic estimates of the differences between regularized solutions.