PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Sample Complexity of Classifiers Taking Values in R^Q, Application to Multi-Class SVMs
Yann Guermeur
Communications in Statistics - Theory and Methods Volume 39, Number 3, pp. 543-557, 2010.


Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such "VC dimensions" exist for models taking values in {0, 1}, {1, ..., Q} and R. We introduce the generalizations appropriate for the missing case, the one of models with values in R^Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:4299
Deposited By:Yann Guermeur
Deposited On:24 March 2009