Jorma Rissanen  Home/Search
Context Related
| cs.tut.fi/~rissanen/papers/bound2.ps Cached: PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
PS.gz PS Image Update HelpFrom: cs.tut.fi/~rissanen/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We show that the normalized maximum likelihood (NML) distribution as a universal code for a parametric class of models is closest to the negative logarithm of the maximized likelihood in the mean code length distance, where the mean is taken with respect to the worst case model inside or outside the parametric class. We strengthen this result by showing that, when the data generating models are restricted to be the most `benevolent' ones in that they incorporate all the constraints in the ... (Update)
Similar documents based on text: More All
0.3: Complexity of Simple Nonlogarithmic Loss Functions - Rissanen (2001) (Correct)
0.3: Lectures on Statistical Modeling Theory - Rissanen (2005) (Correct)
0.2: Universal Codes for Finite Sequences of Integers Drawn From .. - Foster, Stine, Wyner (2001) (Correct)
BibTeX entry: (Update)
Rissanen, J. (2001), `Strong Optimality of the Normalized ML Models as Universal Codes and Information in Data', IEEE Trans. Information Theory (to appear) http://citeseer.ist.psu.edu/rissanen00strong.html More
@article{ rissanen01strong,
author = "Rissanen",
title = "Strong Optimality of the Normalized {ML} Models as Universal Codes and Information in Data",
journal = "IEEETIT: IEEE Transactions on Information Theory",
volume = "47",
year = "2001",
url = "citeseer.ist.psu.edu/rissanen00strong.html" }
Citations (may not include all citations):417 Stochastic Complexity in Statistical Inquiry (context) - Rissanen - 1989
139 Stochastic Complexity and Modeling (context) - Rissanen - 1986
93 Fisher Information and Stochastic Complexity (context) - Rissanen - 1996
78 Universal Coding, Information, Prediction, and Estimation (context) - Rissanen - 1984
67 Information-Theoretic Asymptotics of Bayes Methods (context) - Clarke, Barron - 1990
49 Universal Sequential Coding of Single Messages (context) - Yu - 1987
46 Universal Noiseless Coding (context) - Davisson - 1973
34 A Strong Version of the Redundancy-Capacity Theorem of Unive.. (context) - Merhav, Feder - 1995
23 The Minimum Description Length Principle and reasoning under.. (context) - Grunwald - 1998
10 MDL Denoising - Rissanen - 2000
10 The MDL Principle in Modeling and Coding (context) - Barron, Rissanen et al. - 1998
8 and specification analysis (context) - White - 1994
2 Iterated Logarithmic Expansions of the Pathwise Code Lengths.. - Li, Yu - 2000
2 A Geometric Formulation of Occam (context) - Balasubramanian - 1996
2 Robustly Minimax Codes for Universal Data Compression (context) - Jun-ichi, Andrew - 1998
[Article contains additional citations not shown here]
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.tut.fi/~rissanen/): More
Hypothesis Selection and Testing by the MDL Principle - Rissanen (1998) (Correct)
MDL Denoising - Rissanen (1999) (Correct)
Strong Optimality of the Normalized ML Models as Universal Codes - Rissanen (2000) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC