Generalization Bounds for Convex Combinations of Kernel Functions

Smola, AJ; Williamson, RC; Schölkopf, B

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Report

Generalization Bounds for Convex Combinations of Kernel Functions

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.41.1911&rep=rep1&type=pdf
(Any fulltext)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Smola, A., Williamson, R., & Schölkopf, B.(1998). Generalization Bounds for Convex Combinations of Kernel Functions (NC2-TR-1998-022). London, UK: University of London, Royal Holloway College, NeuroCOLT 2.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-E977-F

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.