logo Idiap Research Institute        
 [BibTeX] [Marc21]
Sparse Probabilistic Classifiers
Type of publication: Idiap-RR
Citation: grandvalet:rr07-19
Number: Idiap-RR-19-2007
Year: 2007
Institution: IDIAP
Note: To appear in \textit{Proceedings of the $\mathit{24}^{th}$ International Conference on Machine Learning}, Corvallis, OR, 2007
Abstract: The scores returned by support vector machines are often used as a confidence measures in the classification of new examples. However, there is no theoretical argument sustaining this practice. Thus, when classification uncertainty has to be assessed, it is safer to resort to classifiers estimating conditional probabilities of class labels. Here, we focus on the ambiguity in the vicinity of the boundary decision. We propose an adaptation of maximum likelihood estimation, instantiated on logistic regression. The model outputs proper conditional probabilities into a user-defined interval and is less precise elsewhere. The model is also sparse, in the sense that few examples contribute to the solution. The computational efficiency is thus improved compared to logistic regression. Furthermore, preliminary experiments show improvements over standard logistic regression and performances similar to support vector machines.
Userfields: ipdmembership={learning},
Keywords:
Projects Idiap
Authors Hérault, Romain
Grandvalet, Yves
Crossref by grandvalet:ICML-2:2007
Added by: [UNK]
Total mark: 0
Attachments
  • grandvalet-idiap-rr-07-19.pdf
  • grandvalet-idiap-rr-07-19.ps.gz
Notes