PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Redundancy of the Context-tree Weighting Method on Renewal and Markov Renewal Processes
Aurelien Garivier
IEEE Transactions on Information Theory Volume 52, 2006.

Abstract

The Context Tree Weighting method is almost adaptive on the classes of renewal and Markov renewal processes : it achieves the minimax pointwise redundancy, studied by Imre Csisz\'ar and Paul C. Shields, up to logarithmic factor. On a theoretical level, this result may be regarded as adaptive estimation in a non parametric setting. On a more practical level, this result furnishes a first example of a universal coder efficient on intermediate complexity classes.

??
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:632
Deposited By:Aurelien Garivier
Deposited On:29 December 2004