Header logo is

Hilbertian Metrics on Probability Measures and their Application in SVM's

2004

Conference Paper

ei


The goal of this article is to investigate the field of Hilbertian metrics on probability measures. Since they are very versatile and can therefore be applied in various problems they are of great interest in kernel methods. Quit recently Tops{o}e and Fuglede introduced a family of Hilbertian metrics on probability measures. We give basic properties of the Hilbertian metrics of this family and other used metrics in the literature. Then we propose an extension of the considered metrics which incorporates structural information of the probability space into the Hilbertian metric. Finally we compare all proposed metrics in an image and text classification problem using histogram data.

Author(s): Hein, H. and Lal, TN. and Bousquet, O.
Journal: Pattern Recognition, Proceedings of th 26th DAGM Symposium
Volume: 3175
Pages: 270-277
Year: 2004
Day: 0
Series: Lecture Notes in Computer Science
Editors: Rasmussen, C. E., H. H. B{\"u}lthoff, M. Giese and B. Sch{\"o}lkopf

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: Pattern Recognition, Proceedings of th 26th DAGM Symposium

Digital: 0
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
PostScript

BibTex

@inproceedings{2786,
  title = {Hilbertian Metrics on Probability Measures and their Application in SVM's},
  author = {Hein, H. and Lal, TN. and Bousquet, O.},
  journal = {Pattern Recognition, Proceedings of th 26th DAGM Symposium},
  volume = {3175},
  pages = {270-277},
  series = {Lecture Notes in Computer Science},
  editors = {Rasmussen, C. E., H. H. B{\"u}lthoff, M. Giese and B. Sch{\"o}lkopf},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  year = {2004}
}