Institute Homepage DE Sign In

Back

Empirical Inference Poster 2007

A Hilbert Space Embedding for Distributions

no image
Empirical Inference
Arthur Gretton
Thumb ticker sm l1170153
Empirical Inference
Bernhard Schölkopf
  • Director

While kernel methods are the basis of many popular techniques in supervised learning, they are less commonly used in testing, estimation, and analysis of probability distributions, where information theoretic approaches rule the roost. However it becomes difficult to estimate mutual information or entropy if the data are high dimensional.

Author(s): Smola, AJ. and Gretton, A. and Song, L. and Schölkopf, B.
Journal: Proceedings of the 10th International Conference on Discovery Science (DS 2007)
Volume: 10
Pages: 40-41
Year: 2007
Month: October
Day: 0
Bibtex Type: Poster (poster)
Digital: 0
DOI: 10.1007/978-3-540-75488-6_5
Electronic Archiving: grant_archive
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik
Links:

BibTex 

@poster{4644,
  title = {A Hilbert Space Embedding for Distributions},
  journal = {Proceedings of the 10th International Conference on Discovery Science (DS 2007)},
  abstract = {While kernel methods are the basis of many popular techniques in supervised learning, they are less commonly used in testing, estimation, and analysis of probability distributions, where information theoretic approaches rule the roost. However it becomes difficult to estimate mutual information or entropy if the data are high dimensional.},
  volume = {10},
  pages = {40-41},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = oct,
  year = {2007},
  slug = {4644},
  author = {Smola, AJ. and Gretton, A. and Song, L. and Sch{\"o}lkopf, B.},
  month_numeric = {10}
}