We discuss the properties of Jeffreys mixture for a Markov model. First, we show that a
modified Jeffreys mixture asymptotically achieves the minimax coding regret for universal …

We shall generalize BS Clarke and AR Barron's analysis of the Bayes method for the FSMX
sources. The FSMX source considered here is specified by the set of all states and its …

This report contains the results of a study that was performed by the Information and
Communication Theory Group of Eindhoven University for KPN Research in Leidschendam …

In this paper, we discuss the difference in code lengths between the code based on the
minimum description length (MDL) principle (the MDL code) and the Bayes code under the …

We propose a variation of the Context Tree Weighting algorithm for tree source modified
such that the growth of the context resembles Lempel-Ziv parsing. We analyze this …

We give an approximation formula for the predictive Bayes code for FSMX models
(subspaces of Markov models). Moreover, we empirically show that the code using our …

We discuss the properties of Jeffreys mixture for general FSMX model (a certain class of
Markov sources [11]). First, we show that modified Jeffreys mixture asymptotically achieves …

Prediction of actual symbol probability is crucial for statistical data compression that uses
arithmetic coder. Krichevsky-Trofimov (KT) estimator has been a standard predictor and …

A zero-redundancy estimator is defined by a weighted sum of Krichevsky-Trofimov (KT)
sequential probability estimators ie, the minimax Bayes of the memoryless process, over all …

This paper explores a relationship between parameters for the context tree weighting and
weights for a general model weighting technique. In particular, an algorithm is proposed that …