
Concentration Inequalities and Model Selection
Ecole d'Eté de Probabilités de Saint-Flour XXXIII - 2003
Pascal Massart(Author)
Jean Picard(Editor)
Springer (Publisher)
1st Edition
Published on 18. April 2007
Book
Paperback/Softback
XIV, 343 pages
978-3-540-48497-4 (ISBN)
Description
Concentration inequalities have been recognized as fundamental tools in several domains such as geometry of Banach spaces or random combinatorics. They also turn to be essential tools to develop a non asymptotic theory in statistics. This volume provides an overview of a non asymptotic theory for model selection. It also discusses some selected applications to variable selection, change points detection and statistical learning.
More details
Product info
Book
Series
Band 1896
Language
English
Place of publication
Berlin, Heidelberg
Germany
Target group
Research
Illustrations
Bibliographie
Dimensions
Height: 236 mm
Width: 157 mm
Thickness: 22 mm
Weight
549 gr
ISBN-13
978-3-540-48497-4 (9783540484974)
DOI
10.1007/978-3-540-48503-2
Schweitzer Classification
Persons
Prof. Massart has received the bronze medal of the CNRS (in mathematics and theoretical physics) in 1988 and the COPPS Presidents' award in 1998.
Content
Exponential and Information Inequalities.- Gaussian Processes.- Gaussian Model Selection.- Concentration Inequalities.- Maximal Inequalities.- Density Estimation via Model Selection.- Statistical Learning.