A Pattern Search Method for Model Selection of Support Vector Regression

  title={A Pattern Search Method for Model Selection of Support Vector Regression},
  author={Michinari Momma and Kristin P. Bennett},
We develop a fully-automatic pattern search methodology for model selection of support vector machines (SVMs) for regression and classification. Pattern search (PS) is a derivative-free optimization method suitable for low-dimensional optimization problems for which it is difficult or impossible to calculate derivatives. The methodology was motivated by an application in drug design in which regression models are constructed based on a few high-dimensional examplars. Automatic model selection… CONTINUE READING
Highly Cited
This paper has 149 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 84 extracted citations

149 Citations

Citations per Year
Semantic Scholar estimates that this publication has 149 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 16 references

Support Vector Machines for Large-Scale Regression Problems, IDIAP-RR-00-17

R. Collobert, Samy Bengio
View 3 Excerpts
Highly Influenced

Choosing kernel parameters for support vector machines

O. Chapelle, V. Vapnik, O. Bousquet, S. Mukherjee
AT&T Labs Technical report • 2000
View 2 Excerpts

Shrink - ing the tube : a new support vector regression algorithm

Advances in Neural Information Processing Systems • 2000

The Nature of Statistical Learning Theory

Statistics for Engineering and Information Science • 2000
View 2 Excerpts

Two Efficient Methods for Computing Leave-One-Out Error in SVM Algorithms

S. S. Keerthi, C. J. Ong, Martin M.S. Lee
Technical Report, • 2000
View 1 Excerpt

Comparitive QSAR Studies on Anti-HIV Drugs

R. Garg, S. P. Gupta, +3 authors C. Hansch
Chem. Rev. • 1999
View 1 Excerpt

Similar Papers

Loading similar papers…