1.

Record Nr.

UNISA996466607003316

Autore

Massart Pascal

Titolo

Concentration Inequalities and Model Selection [[electronic resource] ] : Ecole d'Eté de Probabilités de Saint-Flour XXXIII - 2003 / / by Pascal Massart ; edited by Jean Picard

Pubbl/distr/stampa

Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 2007

ISBN

1-280-85333-6

9786610853335

3-540-48503-1

Edizione

[1st ed. 2007.]

Descrizione fisica

1 online resource (345 p.)

Collana

École d'Été de Probabilités de Saint-Flour, , 0721-5363 ; ; 1896

Classificazione

31.70

Disciplina

511/.8

Soggetti

Probabilities

Statistics 

Information theory

Probability Theory and Stochastic Processes

Statistical Theory and Methods

Information and Communication, Circuits

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Note generali

Description based upon print version of record.

Nota di bibliografia

Includes bibliographical references (p. [319]-324) and index.

Nota di contenuto

Exponential and Information Inequalities -- Gaussian Processes -- Gaussian Model Selection -- Concentration Inequalities -- Maximal Inequalities -- Density Estimation via Model Selection -- Statistical Learning.

Sommario/riassunto

Since the impressive works of Talagrand, concentration inequalities have been recognized as fundamental tools in several domains such as geometry of Banach spaces or random combinatorics. They also turn out to be essential tools to develop a non-asymptotic theory in statistics, exactly as the central limit theorem and large deviations are known to play a central part in the asymptotic theory. An overview of a non-asymptotic theory for model selection is given here and some selected applications to variable selection, change points detection and statistical learning are discussed. This volume reflects the content of the course given by P. Massart in St. Flour in 2003. It is mostly self-



contained and accessible to graduate students.