Contact The MIT Press Information on how to order from The MIT Press Access your saved shopping cart, e-mail list subscriptions, order history, address book, and other info in the Your Profile area MIT Press Home Page


June 2007
8 x 10, 504 pp., 12 illus.
$47.00/£34.95 (CLOTH)
Short

ISBN-10:
0-262-07281-5
ISBN-13:
978-0-262-07281-6

Series
Adaptive Computation and Machine Learning
Related Links
Open this site in a new browser window.
Find this book in a library
Request Exam/Desk Copy

Welcome, Technology Review Subscriber!
The MIT Press is pleased to offer you a 20% discount on our books. To claim your discount, simply click the "add to cart" button and proceed to the checkout.

The Minimum Description Length Principle
Peter D. Grünwald
Foreword by Jorma Rissanen


Table of Contents and Sample Chapters

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 data. MDL methods are particularly well-suited for dealing with model selection, prediction, and estimation problems in situations where the models under consideration can be arbitrarily complex, and overfitting the data is a serious concern.

This extensive, step-by-step introduction to the MDL Principle provides a comprehensive reference (with an emphasis on conceptual issues) that is accessible to graduate students and researchers in statistics, pattern classification, machine learning, and data mining, to philosophers interested in the foundations of statistics, and to researchers in other applied sciences that involve model selection, including biology, econometrics, and experimental psychology. Part I provides a basic introduction to MDL and an overview of the concepts in statistics and information theory needed to understand MDL. Part II treats universal coding, the information-theoretic notion on which MDL is built, and part III gives a formal treatment of MDL theory as a theory of inductive inference based on universal coding. Part IV provides a comprehensive overview of the statistical theory of exponential families with an emphasis on their information-theoretic properties. The text includes a number of summaries, paragraphs offering the reader a "fast track" through the material, and boxes highlighting the most important concepts.

About the Author

Peter D. Grünwald is a researcher at CWI, the National Research Institute for Mathematics and Computer Science, Amsterdam, the Netherlands. He is also affiliated with EURANDOM, the European Research Institute for the Study of Stochastic Phenomena, Eindhoven, the Netherlands.




See Other Titles In:
Computer Science and Intelligent Systems
 Scientific & Engineering Computation
 Theory of Computation
Economics, Finance, and Business
 Statistics
 
Join an E-mail Alert List


 
 
TECHNOLOGY PARTNER: Azility, Inc. TERMS OF USE | PRIVACY POLICY | COPYRIGHT © 2009