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


List of Figuresxix
Series Forewordxxi
Forewordxxiii
Preface
Download Chapter as PDF Sample Chapter - Download PDF (86 KB)
xxv
IIntroductory Material1
1Learning, Regularity, and Compression
Download Chapter as PDF Sample Chapter - Download PDF (370 KB)
3
2Probabilistic and Statistical Preliminaries41
3Information-Theoretic Preliminaries79
4Information-Theoretic Properties of Statistical Models109
5Crude Two-Part Code MDL131
IIUniversal Coding165
6Universal Coding with Countable Models171
7Parametric Models: Normalized Maximum Likelihood207
8Parametric Models: Bayes231
9Parametric Models: Prequential Plug-in257
10Parametric Models: Two-Part271
11NML With Infinite Complexity295
12Linear Regression335
13Beyond Parametrics369
IIIRefined MDL403
14MDL Model Selection409
15MDL Prediction and Estimation459
16MDL Consistency and Convergence501
17MDL in Context523
IVAdditional Background597
18The Exponential or "Maximum Entropy" Families599
19Information-Theoretic Properties of Exponential Families623
References651
List of Symbols675
Subject Index
Download Chapter as PDF Sample Chapter - Download PDF (142 KB)
679
 
Join an E-mail Alert List


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