Advances in Minimum Description Length: Theory and Applications (Hardcover) (最小描述長度的進展：理論與應用)

Description:

The process of inductive inference -- to infer general laws and principles from particular instances -- is the basis of statistical modeling, pattern recognition, and machine learning. The Minimum Descriptive Length (MDL) principle, a powerful method of inductive inference, holds that the best explanation, given a limited set of observed data, is the one that permits the greatest compression of the data -- that the more we are able to compress the data, the more we learn about the regularities underlying the data. Advances in Minimum Description Length is a sourcebook that will introduce the scientific community to the foundations of MDL, recent theoretical advances, and practical applications.

The book begins with an extensive tutorial on MDL, covering its theoretical underpinnings, practical implications as well as its various interpretations, and its underlying philosophy. The tutorial includes a brief history of MDL -- from its roots in the notion of Kolmogorov complexity to the beginning of MDL proper. The book then presents recent theoretical advances, introducing modern MDL methods in a way that is accessible to readers from many different scientific fields. The book concludes with examples of how to apply MDL in research settings that range from bioinformatics and machine learning to psychology.

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.

In Jae Myung is Professor in the Department of Psychology and a member of the Center for Cognitive Science at Ohio State University.

Mark A. Pitt is Professor in the Department of Psychology and a member of the Center for Cognitive Science at Ohio State University.

 

Table of Contents:

Series Foreword	vii
	Preface	ix
I	Introductory Chapters	1
1	Introducing the Minimum Description Length Principle Peter D. Grünwald	3
2	Minimum Description Length Tutorial Peter D. Grünwald	23
3	MDL, Bayesian Inference, and the Geometry of the Space of Probability Distributions Vijay Balasubramanian	81
4	Hypothesis Testing for Poisson vs. Geometric Distributions Using Stochastic Complexity Aaron D. Lanterman	99
5	Applications of MDL to Selected Families of Models Andrew J. Hanson and Philip Chi-Wing Fu	125
6	Algorithmic Statistics and Kolmogorov's Structure Functions Paul Vitányi	151
II	Theoretical Advances	175
7	Exact Minimax Predictive Density Estimation and MDL Feng Liang and Andrew Barron	177
8	The Contribution of Parameters to Stochastic Complexity Dean P. Foster and Robert A. Stine	195
9	Extended Stochastic Complexity and Its Applications to Learning Kenji Yamanishi	215
10	Kolmogorov's Structure Function in MDL Theory and Lossy Data Compression Jorma Rissanen and Ioan Tabus	245
III	Practical Applications	263
11	Minimum Message Length and Generalized Bayesian Nets with Asymmetric Languages Joshua W. Comley and David L. Dowe	265
12	Simultaneous Clustering and Subset Selection via MDL Rebecka Jörnsten and Bin Yu	295
13	An MDL Framework for Data Clustering Petri Kontkanen, Petri Myllymäki, Wray Buntine, Jorma Rissanen and Henry Tirri	323
14	Minimum Description Length and Psychological Clustering Models Michael D. Lee and Daniel J. Navarro	355
15	A Minimum Description Length Principle for Perception Nick Chater	385
16	Minimum Description Length and Cognitive Modeling Yong Su, In Jae Myung and Mark A. Pitt	411
	Index	435