Marius Kloft and Ulrich Rückert and Peter Bartlett

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2010-49

May 4, 2010

http://www2.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},
    Year= {2010},
    Month= {May},
    Url= {http://www2.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://www2.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-49.html
%F Kloft:EECS-2010-49