A Tutorial Introduction to the Minimum Description Length Principle

作者: Peter Grünwald

DOI:

关键词: Mathematical statisticsSpring (mathematics)CalculusMinimum description lengthBasis (linear algebra)MathematicsSubject (documents)Algorithm

摘要: This tutorial provides an overview of and introduction to Rissanen's Minimum Description Length (MDL) Principle. The first chapter a conceptual, entirely non-technical the subject. It serves as basis for technical given in second chapter, which all ideas are made mathematically precise. main discussed great conceptual detail. is extended version two chapters collection "Advances Length: Theory Application" (edited by P.Grunwald, I.J. Myung M. Pitt, be published MIT Press, Spring 2005).

参考文章(68)
A. Barron, J. Rissanen, Bin Yu, The minimum description length principle in coding and modeling IEEE Transactions on Information Theory. ,vol. 44, pp. 2743- 2760 ,(1998) , 10.1109/18.720554
K. Yamanishi, A decision-theoretic extension of stochastic complexity and its applications to learning IEEE Transactions on Information Theory. ,vol. 44, pp. 1424- 1439 ,(1998) , 10.1109/18.681319
I. Csiszar, P.C. Shields, The consistency of the BIC Markov order estimator international symposium on information theory. pp. 26- ,(2000) , 10.1109/ISIT.2000.866316
Jorma Rissanen, A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH Annals of Statistics. ,vol. 11, pp. 416- 431 ,(1983) , 10.1214/AOS/1176346150
C. S. Wallace, D. M. Boulton, An Information Measure for Classification The Computer Journal. ,vol. 11, pp. 185- 194 ,(1968) , 10.1093/COMJNL/11.2.185
Peter Grünwald, Maximum entropy and the glasses you are looking through uncertainty in artificial intelligence. pp. 238- 246 ,(2000)
N. L. Hjort, Brian D. Ripley, Pattern recognition and neural networks ,(1996)
N. Vereshchagin, P. Vitanyi, Kolmogorov's structure functions with an application to the foundations of model selection foundations of computer science. pp. 751- 760 ,(2002) , 10.1109/SFCS.2002.1182000