vers le site de l'ENS
Lien vers l'accueil
lancer la recherche

» Conférences d’après mars 2011 : nouveau site


Journée Mathematical Foundations of Learning Theory

< précédent | suivant >

Is There Life beyond the Classification Problem?
Nicolas Vayatis (univ. Paris VI)

3 juin 2006

In the recent years, significant progress has been achieved on the statistical understanding of celebrated classification algorithms such as boosting and SVM. The key for proceeding to a statistical analysis was to interpret these algorithms as optimization procedures minimizing a penalized convex risk functional. From there it was possible: first, to relate the convex criterion to the standard performance measure -the classification error- and then, to adapt the flourishing theory of empirical risk minimization in order to provide generalization error bounds and oracle inequalities for convex risk minimization procedures. In the talk, I will discuss whether this programme can be applied to another problem: the ranking/scoring problem. Indeed, in applications such as Information Retrieval or Credit Risk screening, the goal is to rank/score webpages or individuals, rather than simply assigning them to a specified category. In this perspective, standard performance measures lead to statistical functionals of order two for which classification theory does not apply straightforwardly. In the talk, I will give some insights and results on these new challenging issues.
(Joint work with Stephan Clémençon and Gabor Lugosi.)

pictogrammeformat pdf - 977.18 Ko

pictogrammeformat audio mp3 - ??? (erreur acces)

- Visualiser
- Télécharger
pictogrammeformat quicktime mov, vidéo à la demande

pictogrammeformat mp4, vidéo à télécharger - 104.94 Mo

pictogrammeformat windows media video - 70.12 Mo

Nicolas Vayatis Nicolas Vayatis (univ. Paris VI)
Laboratoire de Probabilités et Modèles Aléatoires