PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Conditional NML universal models
Jorma Rissanen and Teemu Roos
In: Information Theory and Applications Workshop (ITA-07), 29 Jan - 02 Feb 2007, San Diego, CA.

Abstract

The NML (Normalized Maximum Likelihood) universal model has certain minmax optimal properties but it has two shortcomings: the normalizing coefficient can be evaluated in a closed form only for special model classes, and it does not define a random process so that it cannot be used for prediction. We present a universal conditional NML model, which has minmax optimal properties similar to those of the regular NML model. However, unlike NML, the conditional NML model defines a random process which can be used for prediction. It also admits a recursive evaluation for data compression.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Invited Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:2972
Deposited By:Teemu Roos
Deposited On:26 March 2007