ebook img

The Minimum Description Length Principle (Adaptive Computation and Machine Learning) PDF

738 Pages·2007·3.02 MB·English
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview The Minimum Description Length Principle (Adaptive Computation and Machine Learning)

the computer science/statistics t h e The Minimum Description Length Principle M Peter D. Grünwald i foreword by Jorma Rissanen n i m The minimum description length (MDL) principle is a powerful method of inductive u inference, the basis of statistical modeling, pattern recognition, and machine m Minimum learning. It holds that the best explanation, given a limited set of observed data, D is the one that permits the greatest compression of the data. MDL methods are e particularly well suited for dealing with model selection, prediction, and estimation s c problems in situations where the models under consideration can be arbitrarily r i complex, and overfitting the data is a serious concern. p This extensive, step-by-step introduction to the MDL principle provides a t i PETER D. GRÜNWALD comprehensive reference (with an emphasis on conceptual issues) that is accessible o n to graduate students and researchers in statistics, pattern classification, machine L Description learning, and data mining, to philosophers interested in the foundations of e statistics, and to researchers in other applied sciences that involve model selection, n including biology, econometrics, and experimental psychology. Part I provides a basic g t introduction to MDL and an overview of the concepts in statistics and information h theory needed to understand MDL. Part II treats universal coding, the information- p theoretic notion on which MDL is built, and part III gives a formal treatment of MDL r i theory as a theory of inductive inference based on universal coding. Part IV provides n c a comprehensive overview of the statistical theory of exponential families with an i p emphasis on their information-theoretic properties. The text includes a number of Length l e summaries, paragraphs offering the reader a “fast track” through the material, and boxes highlighting the most important concepts. Peter D. Grünwald is Senior Researcher and Project Leader at CWI, the National G Research Institute for Mathematics and Computer Science in Amsterdam, and is R Ü affiliated with EURANDOM at Eindhoven University of Technology, the Netherlands. N W He is the coeditor of Advances in Minimum Description Length: Theory and A L Applications (MIT Press, 2005). D principle Adaptive Computation and Machine Learning series 0-262-07281-5 The MIT Press 978-0-262-07281-6 Massachusetts Institute of Technology Cambridge, Massachusetts 02142 http://mitpress.mit.edu foreword by Jorma Rissanen The Minimum Description Length Principle The Minimum Description Length Principle PeterD.Grünwald TheMITPress Cambridge,Massachusetts London,England ©2007MassachusettsInstituteofTechnology All rights reserved. No part of this book may be reproducedin any form by any electronicormechanicalmeans(includingphotocopying,recording,orinformation storageandretrieval)withoutpermissioninwritingfromthepublisher. TypesetinPalatinobytheauthorusingLATEX2εwithC.Manning’sfbook.clsand statnlpbook.stymacros. PrintedandboundintheUnitedStatesofAmerica. LibraryofCongressCataloging-in-PublicationInformation Grünwald,PeterD. Theminimumdescriptionlengthprinciple/PeterD.Grünwald. p. cm.—(Adaptivecomputationandmachinelearning) Includesbibliographicalreferencesandindex. ISBN-13:978-0-262-07281-6(alk.paper) 1.Minimumdescriptionlength(Informationtheory)I.Title QA276.9G782007 003’.54—dc22 2006046646 10987654321 Tomyfather Brief Contents I IntroductoryMaterial 1 1 Learning,Regularity,andCompression 3 2 ProbabilisticandStatisticalPreliminaries 41 3 Information-TheoreticPreliminaries 79 4 Information-TheoreticPropertiesofStatisticalModels 109 5 CrudeTwo-PartCodeMDL 131 II UniversalCoding 165 6 UniversalCodingwithCountableModels 171 7 ParametricModels:NormalizedMaximumLikelihood 207 8 ParametricModels:Bayes 231 9 ParametricModels:PrequentialPlug-in 257 10 ParametricModels:Two-Part 271 11 NMLWithInfiniteComplexity 295 12 LinearRegression 335 13 BeyondParametrics 369 III RefinedMDL 403 14 MDLModelSelection 409 15 MDLPredictionandEstimation 459 16 MDLConsistencyandConvergence 501 17 MDLinContext 523 viii BriefContents IV AdditionalBackground 597 18 TheExponentialor“MaximumEntropy”Families 599 19 Information-TheoreticPropertiesofExponentialFamilies 623

Description:
The minimum description length (MDL) principle is a powerful method of inductive inference, the basis of statistical modeling, pattern recognition, and machine learning. It holds that the best explanation, given a limited set of observed data, is the one that permits the greatest compression of the
See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.