Support Vector Median Regression

  • Hwang, Chang-Ha (Dept. of Statistical Information, Catholic University of Daegu)
  • Published : 2003.02.28

Abstract

Median regression analysis has robustness properties which make it an attractive alternative to regression based on the mean. Support vector machine (SVM) is used widely in real-world regression tasks. In this paper, we propose a new SV median regression based on check function. And we illustrate how this proposed SVM performs and compare this with the SVM based on absolute deviation loss function.

References

  1. ISIS Technical Report, U. of Southampton Support Vector Machines for Classification and Regression Gunn, S.
  2. Econometrica v.46 Regression Quantiles Koenker, R.;Bassett, G.
  3. Journal of Economic Perspectives v.40 no.4 Quantile Regression Koenker R.;Hallock K.F.
  4. Communications in Statistics v.31 no.10 Prediction Intervals for Support Vector Machine Regression Seok, K.;Hwang C.;Cho D.
  5. Algorithmica v.22 On a kernel-based method for pattern recognition, regression, approximation and operator inversion Smola A.;Schoelkopf B.
  6. The Nature of Statistical Learning Theory Vapnik V. N.
  7. Statistical Learning Theory Vapnik V. N.
  8. Quantile regression : applications and current research area Yu K.;Lu Z.;Stande J.