Affordable Access

Access to the full text

Choosing Multiple Parameters for Support Vector Machines

Authors
  • Chapelle, Olivier1
  • Vapnik, Vladimir2
  • Bousquet, Olivier3
  • Mukherjee, Sayan4
  • 1 LIP6, Paris, France , Paris
  • 2 AT&T Research Labs, 200 Laurel Ave, Middletown, NJ, 07748, USA , Middletown
  • 3 École Polytechnique, France
  • 4 MIT, Cambridge, MA, 02139, USA , Cambridge
Type
Published Article
Journal
Machine Learning
Publisher
Kluwer Academic Publishers
Publication Date
Jan 01, 2002
Volume
46
Issue
1-3
Pages
131–159
Identifiers
DOI: 10.1023/A:1012450327387
Source
Springer Nature
Keywords
License
Yellow

Abstract

The problem of automatically tuning multiple parameters for pattern recognition Support Vector Machines (SVMs) is considered. This is done by minimizing some estimates of the generalization error of SVMs using a gradient descent algorithm over the set of parameters. Usual methods for choosing parameters, based on exhaustive search become intractable as soon as the number of parameters exceeds two. Some experimental results assess the feasibility of our approach for a large number of parameters (more than 100) and demonstrate an improvement of generalization performance.

Report this publication

Statistics

Seen <100 times