GRETSI'03 19st GRETSI Symposium
on Signal and Image Processing
Paris   8 - 11 september 2003
Welcome Program By Session By Author By Topic By ID

Information related to the paper

Title
Estimating the moments of a random vector with applications
Author(s)
John Shawe-Taylor Royal Holloway, University of London
Nello Cristianini Department of Statistics, UC Davis
Rererences
vol. I, page 47
 Get the paper in PDF format
 
To obtain Acrobat Reader (version 5 minimum required) necessary to his read.

Abstract

A general result about the quality of approximation of the mean of a distribution by its empirical estimate is proven that does not involve the dimension of the feature space. Using the kernel trick this gives also bounds the quality of approximation of higher order moments. A number of applications are derived of interest in learning theory including a new novelty detection algorithm and rigorous bounds on the Robust Minimax Classification algorithm.
Edition : Télécom-Paris -- 2003