Distance-Based Kernels for Real-Valued Data
We consider distance-based similarity measures for real-valued vectors of interest in kernel-based machine learning algorithms. In particular, a truncated Euclidean similarity measure and a self-normalized similarity measure related to the Canberra distance. It is proved that they are positive semi-definite (p.s.d.), thus facilitating their use in kernel-based methods, like the Support Vector Machine, a very popular machine learning tool. These kernels may be better suited than standard kernels (like the RBF) in certain situations, that are described in the paper. Some rather general results concerning positivity properties are presented in detail as well as some interesting ways of proving the p.s.d. property.
Unable to display preview. Download preview PDF.
- BERG, C. CHRISTENSEN, J.P.R. and RESSEL, P. (1984): Harmonic Analysis on Semi-groups: Theory of Positive Definite and Related Functions, Springer.Google Scholar
- CHANDON, J.L. and PINSON, S. (1981): Analyse Typologique. Théorie et Applications, Masson, Paris.Google Scholar
- FOWLKES, C., BELONGIE, S., CHUNG, F., and MALIK, J. (2004): Spectral Grouping Us-ing the Nyström Method. IEEE Trans. on PAMI, 26(2), 214-225.Google Scholar
- HORN, R.A. and JOHNSON, C.R. (1991): Topics in Matrix Analysis, Cambridge University Press.Google Scholar
- KOKARE, M., CHATTERJI, B.N. and BISWAS, P.K. (2003): Comparison of similarity metrics for texture image retrieval. In: IEEE Conf. on Convergent Technologies for AsiaPacific Region, 571-575.Google Scholar
- SHAWE-TAYLOR, J. and CRISTIANINI, N. (2004): Kernel Methods for Pattern Analysis, Cambridge University Press.Google Scholar
- VAPNIK. V. (1998): The Nature of Statistical Learning Theory. Springer-Verlag.Google Scholar