We derive the asymptotics of the redundancy of Bayes rules for Markov chains of fixed order
over a finite alphabet, extending the work of Barron and Clarke (1990) on independent and …

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 …

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 …

We analyze the relationship between a minimum description length (MDL) estimator
(posterior mode) and a Bayes estimator for exponential families. We show the following …

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 …

Abstract The Krichevsky–Trofimov estimator can be implemented as an arithmetic data
compressor based on a finite window. We analyze the redundancy of this estimator for the …

Krichevsky と Trofimov により提案された予測確率推定量は, 有限長の窓に基づいた
推定量に修正することができ, これを用いて非定常な情報源にも適したデータ圧縮アルゴリズムを …

We review the notion of Rissanen's stochastic complexity and the method of modified
Jeffreys mixtures for achieving the stochastic complexity. The stochastic complexity is …

We consider the problem of sequential prediction for classes of Markov sources and their
geometrical structures. A class of Markov sources defined by a context tree (tree model) is …

算術符号を用いた無ひずみデータ圧縮においては, 次文字の確率予測が重要である.
確率予測法として冗長度解析などの理論的研究が進んでいるものに Krichevski-Trofimov …