A Note on Perturbation Results for Learning Empirical Operators

A Note on Perturbation Results for Learning Empirical Operators

A large number of learning algorithms, for example, spectral clustering, kernel Principal Components Analysis and many manifold methods are based on estimating eigenvalues and eigenfunctions of operators defined by a similarity function or a kernel, given empirical data. Thus for the analysis of alg...

Full description

Bibliographic Details
Main Authors: De Vito, Ernesto, Belkin, Mikhail, Rosasco, Lorenzo
Other Authors: Tomaso Poggio
Published: 2008
Subjects:
perturbation theory
statistical learning theory
kernel methods
spectral methods
Online Access:http://hdl.handle.net/1721.1/41940

Internet

http://hdl.handle.net/1721.1/41940

Similar Items