Skip to main content
SpringerLink
Log in

A Study of Tuning Hyperparameters for Support Vector Machines

  • Conference paper
  • First Online:
Computational Science and Its Applications — ICCSA 2003 (ICCSA 2003)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2667))

Included in the following conference series:

Abstract

Automatic parameters selection is an important issue to make support vector machines (SVMs) practically useful. Most existing approaches use Newton method directly to compute the optimal parameters. They treat parameters optimization as an unconstrained optimization problem. In this paper, the limitation of these existing approached is stated and a new methodology to optimize kernel parameters, based on the computation of the gradient of penalty function with respect to the RBF kernel parameters, is proposed. Simulation results reveal the feasibility of this new approach and demonstrate an improvement of generalization ability.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Vapnik V. Statistical learning theory. John Wiley, New York, 1998

    MATH  Google Scholar 

  2. Cristianini N and Shawe-Taylor J. An introduction to support vector machines. Cambridge University Press, 2000

    Google Scholar 

  3. Joachims T. Estimating the generalization performance of a svm efficiently. In proceedings of the inernational conference on machine learning. Morgan Kaufman, 2000

    Google Scholar 

  4. Chapelle O, Vapnik V and Bousquet O et al. Choosing multiple parameters for support vector machines. Machine Learning. 2002, 46: 131–159

    MATH  Google Scholar 

  5. Vapnik V and Chapelle O. Bounds on error expectation for support vector machines. Neural Computation. 2000, 12(9): 5–26

    Article  Google Scholar 

  6. Cortes C and Vapnik V. Support vector networks. Machine Learning. 1995, 20: 273–297

    MATH  Google Scholar 

  7. Muller K R, Mika S et al. An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks. 2001, 12(2): 181–201

    Article  Google Scholar 

  8. Schölkopf B. Support vector learning. R. Oldenbourg Verlag, Munich, 1997

    MATH  Google Scholar 

  9. Ben-Daya M, Al-Sultan K.S. A new penalty function algorithm for convex quadratic programming. European Journal of Operational Research. 1997, 101(1): 155–163

    Article  MATH  Google Scholar 

  10. Gunnar. http://ida.first.gmd.de/~raetsch/data/benchmarks.htm

Download references

Author information

Authors and Affiliations

  1. Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China, 200030

    Yong Quan, Jie Yang & Chengzhou Ye

Authors
  1. Yong Quan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chengzhou Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Army High Performance Computing Research Center, USA

    Vipin Kumar

  2. Department of Computer Science, University of Calgary, Calgary, AB, T2N1N4, Canada

    Marina L. Gavrilova

  3. Heuchera Technologies Inc., 122 9251-8 Yonge Street, Richmond Hill, ON, Canada, L4C 9T3

    Chih Jeng Kenneth Tan

  4. Département d’informatique et de recherche opérationelle, Université de Montréal, Montréal, Québec, H3C 3J7, Canada

    Pierre L’Ecuyer

  5. Department of Computer Science and Engineering, University of Minessota, MN, 55455, USA

    Vipin Kumar

  6. The Queen’s University of Belfast, School of Computer Science, Belfast BT7 1NN, Northern Ireland, UK

    Chih Jeng Kenneth Tan

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Quan, Y., Yang, J., Ye, C. (2003). A Study of Tuning Hyperparameters for Support Vector Machines. In: Kumar, V., Gavrilova, M.L., Tan, C.J.K., L’Ecuyer, P. (eds) Computational Science and Its Applications — ICCSA 2003. ICCSA 2003. Lecture Notes in Computer Science, vol 2667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44839-X_106

Download citation

  • DOI: https://doi.org/10.1007/3-540-44839-X_106

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40155-1

  • Online ISBN: 978-3-540-44839-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation