Cover Image

Statistical learning theory and stochastic optimization : Ecole d'Eté de Probabilités de Saint-Flour XXXI-2001 /

Show other versions (1)

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 p...

Full description

Bibliographic Details
Main Author: Catoni, Olivier
Corporate Authors: SpringerLink (Online service), LINK (Online service), Ecole d'été de probabilités de Saint-Flour
Other Authors: Picard, Jean
Format: Conference Proceeding eBook
Language:English
Published: Berlin : Springer-Verlag, [2004]
Series:Lecture notes in mathematics (Springer-Verlag) ; 1851.
Subjects:
Probabilities > Congresses.
Mathematical statistics > Congresses.
Statistics > Congresses.
Mathematical statistics.
Probabilities.
Statistics.
Electronic books.
Conference proceedings.
Online Access:Connect to the full text of this electronic book
Description
Summary: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.
Item Description:" ... 31st Probability Summer School in Saint-Flour (July 8-25, 2001) ..."--Preface.
Electronic resource.
Physical Description:1 online resource (viii, 272 pages) : illustrations.
Bibliography:Includes bibliographical references and index.
ISBN:9783540445074 (electronic bk.)
3540445072 (electronic bk.)
ISSN:0075-8434 ;