Empirical Inference Technical Report 2004

Fast Binary and Multi-Output Reduced Set Selection

PostScript
no image
Empirical Inference
no image
Empirical Inference

We propose fast algorithms for reducing the number of kernel evaluations in the testing phase for methods such as Support Vector Machines (SVM) and Ridge Regression (RR). For non-sparse methods such as RR this results in significantly improved prediction time. For binary SVMs, which are already sparse in their expansion, the pay off is mainly in the cases of noisy or large-scale problems. However, we then further develop our method for multi-class problems where, after choosing the expansion to find vectors which describe all the hyperplanes jointly, we again achieve significant gains.

Author(s): Weston, J. and Bakir, GH.
Links:
Number (issue): 132
Year: 2004
Month: November
Day: 0
Bibtex Type: Technical Report (techreport)
Electronic Archiving: grant_archive
Institution: Max Planck Institute for Biological Cybernetics, Tübingen, Germany
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

BibTex

@techreport{3014,
  title = {Fast Binary and Multi-Output Reduced Set Selection},
  abstract = {We propose fast algorithms for reducing the number of kernel evaluations in the testing
  phase for methods such as Support Vector Machines (SVM) and Ridge Regression (RR). For
  non-sparse methods such as RR this results in significantly improved prediction time.
  For binary SVMs, which are already sparse in their expansion, the pay off is mainly in
  the cases of noisy or large-scale problems. However, we then further develop our method
  for multi-class problems where, after choosing the expansion to find vectors which
  describe all the hyperplanes jointly, we again achieve significant gains.},
  number = {132},
  organization = {Max-Planck-Gesellschaft},
  institution = {Max Planck Institute for Biological Cybernetics, T{\"u}bingen, Germany},
  school = {Biologische Kybernetik},
  month = nov,
  year = {2004},
  slug = {3014},
  author = {Weston, J. and Bakir, GH.},
  month_numeric = {11}
}