Browsing Computer Science and Artificial Intelligence Lab (CSAIL) by Author "Caponnetto, Andrea"
Now showing items 1-4 of 4
-
Empirical Effective Dimension and Optimal Rates for Regularized Least Squares Algorithm
Caponnetto, Andrea; Rosasco, Lorenzo; Vito, Ernesto De; Verri, Alessandro (2005-05-27)This paper presents an approach to model selection for regularized least-squares on reproducing kernel Hilbert spaces in the semi-supervised setting. The role of effective dimension was recently shown to be crucial in the ... -
Fast Rates for Regularized Least-squares Algorithm
Caponnetto, Andrea; Vito, Ernesto De (2005-04-14)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 ... -
Risk Bounds for Regularized Least-squares Algorithm with Operator-valued kernels
Vito, Ernesto De; Caponnetto, Andrea (2005-05-16)We show that recent results in [3] on risk bounds for regularized least-squares on reproducing kernel Hilbert spaces can be straightforwardly extended to the vector-valued regression setting. We first briefly introduce ... -
Some Properties of Empirical Risk Minimization over Donsker Classes
Caponnetto, Andrea; Rakhlin, Alexander (2005-05-17)We study properties of algorithms which minimize (or almost minimize) empirical error over a Donsker class of functions. We show that the L2-diameter of the set of almost-minimizers is converging to zero in probability. ...