Foundations of Computational Mathematics

, Volume 7, Issue 3, pp 331–368 | Cite as

Optimal Rates for the Regularized Least-Squares Algorithm

  • A. Caponnetto
  • E. De Vito


We develop a theoretical analysis of the performance of the regularized least-square algorithm on a reproducing kernel Hilbert space in the supervised learning setting. The presented results hold in the general framework of vector-valued functions; therefore they can be applied to multitask problems. In particular, we observe that the concept of effective dimension 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. Moreover, a complete minimax analysis of the problem is described, showing that the convergence rates obtained by regularized least-squares estimators are indeed optimal over a suitable class of priors defined by the considered kernel. Finally, we give an improved lower rate result describing worst asymptotic behavior on individual probability measures rather than over classes of priors.


Regularization Parameter Marginal Distribution Optimal Rate Effective Dimension Polish Space 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer 2006

Authors and Affiliations

  1. 1.Department of Computer Science, University of Chicago, 1100 East 58th Street, Chicago, IL 60637 and D.I.S.I., Universita di Genova, Via Dodecaneso 35 16146GenovaItaly
  2. 2.Dipartimento di Matematica, Universita di Modena, Via Campi 213/B, 41100 Modena, Italy and I.N.F.N., Sezione di Genova, Via Dodecaneso 33 16146GenovaItaly

Personalised recommendations