NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-98-022

Generalization Bounds for Convex Combinations of Kernel Functions

Alex J. Smola, GMD
Robert C. Williamson, ANU
Bernhard Schoelkopf, GMD

Keywords: AdaBoost, Arcing, Large Margin, Hard Margin, Soft Margin, Classification, Support Vectors

Received: 07-AUG-98


Abstract
We derive new bounds on covering numbers for hypothesis classes generated by convex combinations of basis functions. These are useful in bounding the generalization performance of algorithms such as RBF-networks, boosting and a new class of linear programming machines similar to SV machines. We show that p-convex combinations with p>1 lead to diverging bounds, whereas for p=1 good bounds in terms of entropy numbers can be obtained. In the case of kernel expansions, significantly better bounds can be obtained depending on the eigenvalues of the corresponding integral operators.

Download Compressed Postscript