On Learning with Integral 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 algorithms, it is an important problem to be able to assess the quality of such approximations. The contribution of our paper is two-fold:

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Lorenzo Rosasco, Mikhail Belkin, Ernesto De Vito
• Keywords: JMLR 2010, Learning Algorithms, Manifold Methods, Principal Components Analysis