English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Generalization Bounds for Convex Combinations of Kernel Functions

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.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Smola, AJ, Author           
Williamson, RC, Author           
Schölkopf, B1, Author           
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 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.

Details

show
hide
Language(s):
 Dates: 1998-08
 Publication Status: Published in print
 Pages: 11
 Publishing info: London, UK : University of London, Royal Holloway College, NeuroCOLT 2
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 1872
Report Nr.: NC2-TR-1998-022
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show