Empirical Effective Dimension and Optimal Rates for Regularized Least Squares Algorithm

Empirical Effective Dimension and Optimal Rates for Regularized Least Squares Algorithm

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 definition of a rule for the choice of the regularization parameter, attainin...

Full description

Bibliographic Details
Main Authors: Caponnetto, Andrea, Rosasco, Lorenzo, Vito, Ernesto De, Verri, Alessandro
Language:en_US
Published: 2005
Subjects:
AI
optimal rates
effective dimension
semi-supervised learning
Online Access:http://hdl.handle.net/1721.1/30548

Internet

http://hdl.handle.net/1721.1/30548

Similar Items