Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

A Unifying View of Multiple Kernel Learning

Marius Kloft, Ulrich Rückert and Peter Bartlett

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2010-49
May 4, 2010

http://www.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-49.pdf

Recent research on multiple kernel learning has lead to a number of approaches for combining kernels in regularized risk minimization. The proposed approaches include different formulations of objectives and varying regularization strategies. In this paper we present a unifying general optimization criterion for multiple kernel learning and show how existing formulations are subsumed as special cases. We also derive the criterion's dual representation, which is suitable for general smooth optimization algorithms. Finally, we evaluate multiple kernel learning in this framework analytically using a Rademacher complexity bound on the generalization error and empirically in a set of experiments.


BibTeX citation:

@techreport{Kloft:EECS-2010-49,
    Author = {Kloft, Marius and Rückert, Ulrich and Bartlett, Peter},
    Title = {A Unifying View of Multiple Kernel Learning},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2010},
    Month = {May},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-49.html},
    Number = {UCB/EECS-2010-49},
    Abstract = {Recent research on multiple kernel learning has lead to a number of approaches for combining kernels in regularized risk minimization. The proposed approaches include different formulations of objectives and varying regularization strategies. In this paper we present a unifying general optimization criterion for multiple kernel learning and show how existing formulations are subsumed as special cases. We also derive the criterion's dual representation, which is suitable for general smooth optimization algorithms. Finally, we evaluate multiple kernel learning in this framework analytically using a Rademacher complexity bound on the generalization error and empirically in a set of experiments.}
}

EndNote citation:

%0 Report
%A Kloft, Marius
%A Rückert, Ulrich
%A Bartlett, Peter
%T A Unifying View of Multiple Kernel Learning
%I EECS Department, University of California, Berkeley
%D 2010
%8 May 4
%@ UCB/EECS-2010-49
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-49.html
%F Kloft:EECS-2010-49