We are experiencing minor difficulties with our submission forms, which we are working to resolve. If you have any issues while submitting items, please contact us at dspace-lib@mit.edu.
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
Abstract
We develop a theoretical analysis of generalization performances of regularized least-squares on reproducing kernel Hilbert spaces for supervised learning. We show that the concept of effective dimension of an integral operator plays a central role in the definition of a criterion for the choice of the regularization parameter as a function of the number of samples. In fact, a minimax analysis is performed which shows asymptotic optimality of the above-mentioned criterion.
