Nantilus
Statistical learning theory and stochastic optimization : Ecole d'été de probabilités de Saint-Flour XXXI-2001
La 4e de couverture indique : "Statistical learning theory is aimed at analyzing complex data with necessarily approximate models. This book is intended for an audience with a graduate background in probability theory and statistics. It will be useful to any reader wondering why it may be a goo...
Enregistré dans:
| Auteurs principaux : | , |
|---|---|
| Collectivité auteur : | |
| Autres auteurs : | |
| Format : | Livre |
| Langue : | anglais |
| Titre complet : | Statistical learning theory and stochastic optimization : Ecole d'été de probabilités de Saint-Flour XXXI-2001 / [course presented by] Olivier Catoni; Editor, Jean Picard |
| Publié : |
Berlin :
Springer
, copyright 2004 |
| Description matérielle : | 1 vol. (VIII-272 p.) |
| Collection : | Lecture notes in mathematics ; 1851 Ecole d'Eté de Probabilités de Saint-Flour ; 31 |
| Sujets : | |
| Documents associés : | Autre format:
Statistical Learning Theory and Stochastic Optimization |
| Résumé : | La 4e de couverture indique : "Statistical learning theory is aimed at analyzing complex data with necessarily approximate models. This book is intended for an audience with a graduate background in probability theory and statistics. It will be useful to any reader wondering why it may be a good idea, to use as is often done in practice a notoriously "wrong'' (i.e. over-simplified) model to predict, estimate or classify. This point of view takes its roots in three fields: information theory, statistical mechanics, and PAC-Bayesian theorems. Results on the large deviations of trajectories of Markov chains with rare transitions are also included. They are meant to provide a better understanding of stochastic optimization algorithms of common use in computing estimators. The author focuses on non-asymptotic bounds of the statistical risk, allowing one to choose adaptively between rich and structured families of models and corresponding estimators. Two mathematical objects pervade the book: entropy and Gibbs measures. The goal is to show how to turn them into versatile and efficient technical tools, that will stimulate further studies and results." |
|---|---|
| Notes : | Conférences données par Olivier Catoni à l'Ecole d'été de théorie des probabilités de Saint-Flour, du 8 au 25 juillet 2001. Les conférences données à cette date par les professeurs Tavaré et Zeitouni sont parues dans le volume 1837 de "Lecture notes in mathematics" |
| Bibliographie : | Bibliogr. p. [261]-265. Index |
| ISBN : | 3-540-22572-2 |