Skip to main content

3 Result(s)

within E. De Vito Remove this filter Math Applications in Computer Science Remove this filter

and

  1. No Access

    Article

    Adaptive Kernel Methods Using the Balancing Principle

    The regularization parameter choice is a fundamental problem in Learning Theory since the performance of most supervised algorithms crucially depends on the choice of one or more of such parameters. In particu...

    E. De Vito, S. Pereverzyev, L. Rosasco in Foundations of Computational Mathematics (2010)

  2. No Access

    Article

    Optimal Rates for the Regularized Least-Squares Algorithm

    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 genera...

    A. Caponnetto, E. De Vito in Foundations of Computational Mathematics (2007)

  3. No Access

    Article

    Model Selection for Regularized Least-Squares Algorithm in Learning Theory

    We investigate the problem of model selection for learning algorithms depending on a continuous parameter. We propose a model selection procedure based on a worst-case analysis and on a data-independent choice...

    E. De Vito, A. Caponnetto, L. Rosasco in Foundations of Computational Mathematics (2005)