Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms.

Yunwen Lei Ürün Dogan Alexander Binder Marius Kloft

Published in: CoRR (2015)

Keyphrases

data dependent
generalization bounds
learning theory
empirical risk minimization
learning problems
uniform convergence
risk bounds
generalization ability
data sets
upper bound
multi class
model selection
theoretical analysis
linear classifiers
reproducing kernel hilbert space
multi class svms