On the Convergence Rate of l(p)-Norm Multiple Kernel Learning

We derive an upper bound on the local Rademacher complexity of l(p)-norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches analyzed the case p - 1 only while our analysis covers all cases 1 <= p <= infinity, assuming the different feature mappings corresponding to the different kernels to be uncorrelated. We also show a lower bound that shows that the bound is tight, and derive consequences regarding excess loss, namely fast convergence rates of the order O( n(-)1+alpha/alpha where alpha is the minimum eigenvalue decay rate of the individual kernels.

Metadaten
Verfasserangaben:	Marius Kloft, Gilles Blanchard GND
ISSN:	1532-4435
Titel des übergeordneten Werks (Englisch):	JOURNAL OF MACHINE LEARNING RESEARCH
Verlag:	MICROTOME PUBL
Verlagsort:	BROOKLINE
Publikationstyp:	Wissenschaftlicher Artikel
Sprache:	Englisch
Jahr der Erstveröffentlichung:	2012
Erscheinungsjahr:	2012
Datum der Freischaltung:	26.03.2017
Freies Schlagwort / Tag:	generalization bounds; learning kernels; local Rademacher complexity; multiple kernel learning
Band:	13
Seitenanzahl:	38
Erste Seite:	2465
Letzte Seite:	2502
Fördernde Institution:	German Science Foundation [DFG MU 987/6-1, RA 1894/1-1]; World Class University Program through the National Research Foundation of Korea; Korean Ministry of Education, Science, and Technology [R31-10008]; European Community [247022]; European Community’s 7th Framework Programme under the PAS-CAL2 Network of Excellence [ICT-216886]