Refine
Has Fulltext
- no (1) (remove)
Year of publication
- 2012 (1)
Document Type
- Article (1)
Language
- English (1)
Is part of the Bibliography
- yes (1)
Keywords
- learning kernels (1) (remove)
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.