Sciweavers

COLT
2004
Springer
14 years 5 months ago
Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results
One of the nice properties of kernel classifiers such as SVMs is that they often produce sparse solutions. However, the decision functions of these classifiers cannot always be u...
Peter L. Bartlett, Ambuj Tewari
COLT
2004
Springer
14 years 5 months ago
Local Complexities for Empirical Risk Minimization
Peter L. Bartlett, Shahar Mendelson, Petra Philips