Multi-Output Learning via Spectral Filtering
Name
MIT-CSAIL-TR-2011-004.pdf
Size
786.23 KB
Format
Adobe PDF
Checksum (MD5)
c73feee75aa79896b98e09e8cddd89b9
Author(s)
Baldassarre, Luca
Rosasco, Lorenzo
Barla, Annalisa
Verri, Alessandro
Advisor(s)
Tomaso Poggio
Date Issued
January 24, 2011
Series/Report no.
MIT-CSAIL-TR-2011-004
CBCL-296
Abstract
In this paper we study a class of regularized kernel methods for vector-valued learning which are based on filtering the spectrum of the kernel matrix. The considered methods include Tikhonov regularization as a special case, as well as interesting alternatives such as vector-valued extensions of L2 boosting. Computational properties are discussed for various examples of kernels for vector-valued functions and the benefits of iterative techniques are illustrated. Generalizing previous results for the scalar case, we show finite sample bounds for the excess risk of the obtained estimator and, in turn, these results allow to prove consistency both for regression and multi-category classification. Finally, we present some promising results of the proposed algorithms on artificial and real data.
Subjects
Computational Learning, Multi-Output Learning, Spectral Methods
Persistent DSpace Link
