English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  On the Complexity of Learning the Kernel Matrix

Bousquet, O., & Herrmann, D. (2003). On the Complexity of Learning the Kernel Matrix. In S. Becker, S. Thrun, & K. Obermayer (Eds.), Advances in Neural Information Processing Systems 15 (pp. 399-406). Cambridge, MA, USA: MIT Press.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-DB4B-4 Version Permalink: https://hdl.handle.net/21.11116/0000-0005-6BE9-D
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
http://papers.nips.cc/paper/2300-on-the-complexity-of-learning-the-kernel-matrix.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Bousquet, O1, 2, Author           
Herrmann, DJL1, 2, Author           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: We investigate data based procedures for selecting the kernel when learning with Support Vector Machines. We provide generalization error bounds by estimating the Rademacher complexities of the corresponding function classes. In particular we obtain a complexity bound for function classes induced by kernels with given eigenvectors, i.e., we allow to vary the spectrum and keep the eigenvectors fix. This bound is only a logarithmic factor bigger than the complexity of the function class induced by a single kernel. However, optimizing the margin over such classes leads to overfitting. We thus propose a suitable way of constraining the class. We use an efficient algorithm to solve the resulting optimization problem, present preliminary experimental results, and compare them
to an alignment-based approach.

Details

show
hide
Language(s):
 Dates: 2003-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 1999
 Degree: -

Event

show
hide
Title: Sixteenth Annual Conference on Neural Information Processing Systems (NIPS 2002)
Place of Event: Vancouver, Canada
Start-/End Date: 2002-12-09 - 2002-12-14

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 15
Source Genre: Proceedings
 Creator(s):
Becker, S, Editor
Thrun, S, Editor
Obermayer, K, Editor
Affiliations:
-
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 399 - 406 Identifier: ISBN: 0-262-02550-7