Statistical Learning Theory and Stochastic Optimization

Olivier Catoni

ISBN 10: 3540225722 / ISBN 13: 9783540225720

Published by Springer Berlin Heidelberg, Springer Berlin Heidelberg Aug 2004, 2004

About this Item

Neuware -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.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 292 pp. Englisch.

Seller Inventory # 9783540225720

Bibliographic Details

• Title: Statistical Learning Theory and Stochastic Optimization
• Publisher: Springer Berlin Heidelberg, Springer Berlin Heidelberg Aug 2004
• Publication Date: 2004
• Language: English
• ISBN 10: 3540225722
• ISBN 13: 9783540225720
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 235W x 155H x 16D millimeters 235 millimeters width by 155 millimeters height by 16 millimeters depth
• Weight: 446 grams

About this title

Synopsis

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.