Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
427427 | Information Processing Letters | 2010 | 6 Pages |
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.