Neural Processing Letters

, Volume 23, Issue 2, pp 133–141 | Cite as

An Equivalence between SILF-SVR and Ordinary Kriging



Support vector regression (SVR) is a powerful learning technique in the framework of statistical learning theory, while Kriging is a well-entrenched prediction method traditionally used in the spatial statistics field. However, the two techniques share the same framework of reproducing kernel Hilbert space. In this paper, we first review the formulations of SILF-SVR where soft insensitive loss function is utilized and ordinary Kriging, and then prove the equivalence between the two techniques under the assumption that the kernel function is substituted by covariance function.


equivalence Kriging soft insensitive loss function support vector regression 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cortes, C., Vapnik, V. 1995Support vector networksMach Learn.20273297Google Scholar
  2. 2.
    Vapnik, V. 2001The Nature of Statistical Learning Theory2Springer-VerlagBerlinGoogle Scholar
  3. 3.
    Vapnik, V. 1998Statistical Learning TheoryWileyNew YorkGoogle Scholar
  4. 4.
    Burges, C.J.C. 1998A tutorial on support vector machines for pattern recognitionKnowl. Disc Data Min.2143Google Scholar
  5. 5.
    Smola, A.J., Schölkopf, B. 2004A tutorial on support vector regressionStat. Comput.14199222CrossRefMathSciNetGoogle Scholar
  6. 6.
    An, W.S., Sun, Y.G. 2005An information-geometrical approach to constructing kernel in support vector regression machinesWang, L.Chen, K.Ong, Y.S. eds. Proceedings of the First International Conference on Natural Computation.ChangshaChina544551LNCS 3610Google Scholar
  7. 7.
    Lin, C.F., Wang, S.D. 2004Training algorithms for fuzzy support vector machines with noisy dataPattern Recogn. Lett.2516471656MathSciNetGoogle Scholar
  8. 8.
    Kivinen, J., Smola, A., Williamson, R.C. 2004Online learning with kernelsIEEE Trans. Signal Proces.5221652176MathSciNetGoogle Scholar
  9. 9.
    Krige, D.G. 1951A statistical approach to some basic mine valuation problems on the WitwatersrandJ. Chem. Metall. Min. Soc. S. Afr.52119139Google Scholar
  10. 10.
    Cressie, N. 1993Statistics for Spatial DataJohn WileyNew YorkGoogle Scholar
  11. 11.
    Matheron, G. 1963Principles of geostatisticsEcon. Geol.5812461266Google Scholar
  12. 12.
    Mallet, J.C. 2002GeomodelingOxford University PressOxfordGoogle Scholar
  13. 13.
    Vazquez, E., Walter, E., Fleury, G. 2005Intrinsic kriging and prior informationAppl. Stoch. Model Bus. Ind.21215226MathSciNetGoogle Scholar
  14. 14.
    Yan, H.,  et al. 2002The parameter estimation of RBF kernel function based on variogramActa Automatica Sinica28450455Google Scholar
  15. 15.
    Chu, W., Keerthi, S.S., Ong, C.J. 2004Bayesian support vector regression using a unified loss functionIEEE Trans. Neural Networks152944CrossRefGoogle Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  1. 1.Department of AutomationUniversity of Science and Technology of ChinaHefeiPeople’s Republic of China
  2. 2.R&D CenterAutomation Research and Design Institute of Metallurgical IndustryBeijingPeople’s Republic of China

Personalised recommendations