Free access article

Issue ESAIM: P&S Volume 9, 2005 Page(s) 323 - 375 DOI 10.1051/ps:2005018

ESAIM: P&S, November 2005, Vol. 9, pp. 323-375
DOI: 10.1051/ps:2005018

Theory of Classification: a Survey of Some Recent Advances

Stéphane Boucheron¹, Olivier Bousquet² and Gábor Lugosi<sup>3

1</sup>  Laboratoire Probabilités et Modèles Aléatoires, CNRS & Université Paris VII, Paris, France.
²  Pertinence SA, 32 rue des Jeûneurs, 75002 Paris, France.
³  Department of Economics, Pompeu Fabra University, Ramon Trias Fargas 25-27, 08005 Barcelona, Spain; lugosi@upf.es

(Received June 18, 2004. Accepted September 12, 2005.)

Abstract
The last few years have witnessed important new developments in the theory and practice of pattern classification. We intend to survey some of the main new ideas that have led to these recent results.

Mathematics Subject Classification. 62G08, 60E15, 68Q32

Key words: Pattern recognition, statistical learning theory, concentration inequalities, empirical processes, model selection.


© EDP Sciences, SMAI 2005

What is OpenURL?