skip to content
Statistical learning theory and stochastic optimization : Ecole d'Eté de Probabilités de Saint-Flour XXXI-2001 Preview this item
ClosePreview this item
Checking...

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

Author: Olivier Catoni; Jean Picard; LINK (Online service)
Publisher: Berlin : Springer-Verlag, ©2004.
Series: Lecture notes in mathematics (Springer-Verlag), 1851.
Edition/Format:   eBook : Document : Conference publication : EnglishView all editions and formats
Database:WorldCat
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  Read more...
Rating:

(not yet rated) 0 with reviews - Be the first.

Subjects
More like this

 

Find a copy online

Links to this item

Find a copy in the library

&AllPage.SpinnerRetrieving; Finding libraries that hold this item...

Details

Genre/Form: Electronic books
Conference proceedings
Congresses
Additional Physical Format: Print version:
Catoni, Olivier.
Statistical learning theory and stochastic optimization.
Berlin : Springer-Verlag, ©2004
(DLC) 2004109143
(OCoLC)56714791
Material Type: Conference publication, Document, Internet resource
Document Type: Internet Resource, Computer File
All Authors / Contributors: Olivier Catoni; Jean Picard; LINK (Online service)
ISBN: 9783540445074 3540445072
OCLC Number: 56508135
Notes: " ... 31st Probability Summer School in Saint-Flour (July 8-25, 2001) ..."--Preface.
Description: 1 online resource (viii, 272 pages) : illustrations.
Contents: Universal Lossless Data Compression --
Links Between Data Compression and Statistical Estimation --
Non Cumulated Mean Risk --
Gibbs Estimators --
Randomized Estimators and Empirical Complexity --
Deviation Inequalities --
Markov Chains with Exponential Transitions --
References --
Index.
Series Title: Lecture notes in mathematics (Springer-Verlag), 1851.
Other Titles: Ecole d'Eté de Probabilités de Saint-Flour XXXI-2001
Responsibility: Olivier Catoni ; editor, Jean Picard.
More information:

Abstract:

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  Read more...

Reviews

Editorial reviews

Publisher Synopsis

From the reviews: "This book is based on a course of lectures given by the author on a circle of ideas lying at the interface of information theory, statistical learning theory and statistical Read more...

 
User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Tags

Be the first.
Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Linked Data


<http://www.worldcat.org/oclc/56508135>
library:oclcnum"56508135"
library:placeOfPublication
library:placeOfPublication
owl:sameAs<info:oclcnum/56508135>
rdf:typeschema:Book
schema:about
schema:about
schema:about
schema:about
schema:about
<http://id.worldcat.org/fast/1012127>
rdf:typeschema:Intangible
schema:name"Mathematical statistics"@en
schema:name"Mathematical statistics."@en
schema:about
schema:about
schema:bookFormatschema:EBook
schema:contributor
schema:contributor
schema:contributor
schema:copyrightYear"2004"
schema:creator
schema:datePublished"2004"
schema:description"Universal Lossless Data Compression -- Links Between Data Compression and Statistical Estimation -- Non Cumulated Mean Risk -- Gibbs Estimators -- Randomized Estimators and Empirical Complexity -- Deviation Inequalities -- Markov Chains with Exponential Transitions -- References -- Index."@en
schema:description"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."@en
schema:exampleOfWork<http://worldcat.org/entity/work/id/14473764>
schema:genre"Conference proceedings"@en
schema:genre"Conference proceedings."@en
schema:genre"Electronic books."@en
schema:inLanguage"en"
schema:name"Ecole d'Eté de Probabilités de Saint-Flour XXXI-2001"@en
schema:name"Statistical learning theory and stochastic optimization Ecole d'Eté de Probabilités de Saint-Flour XXXI-2001"@en
schema:publisher
schema:url<http://dx.doi.org/10.1007/b99352>
schema:url<http://rave.ohiolink.edu/ebooks/ebc/11305972>
schema:url<http://www.springerlink.com/openurl.asp?genre=issue&issn=0075-8434&volume=1851>
schema:url
schema:url<http://springerlink.metapress.com/link.asp?id=MT30WFT73522>
schema:workExample

Content-negotiable representations

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.