A class of prior distributions on context tree models and an efficient algorithm of the Bayes codes assuming it

Toshiyasu Matsushima*, Shigeich Hirasawa

*この研究の対応する著者

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

The CTW(Context Tree Weighting) algorithm is an efficient universal coding algorithm on context tree models. The CTW algorithm has been interpreted as the non-predictive Bayes coding algorithm assuming a special prior distribution over context tree models. An efficient recursive calculation method using a gathering context tree in the CTWalgorithm is well known. Although there exist efficient recursive algorithms for the Bayes codes assuming a special class of prior distributions, the basic property ofthe prior distribution class has been scarcely investigated. In this paper we show the exact definition of a prior distribution class on context tree models that has the similar property to the class of conjugate priors. We show the posterior distribution is also included in the same distribution class as the prior distribution class. So we can also construct an efficient algorithm ofpredictive Bayes codes on context tree models by using the prior distribution class. Lastly the asymptotic mean code length of the codes IS investigated.

本文言語English
ホスト出版物のタイトルISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology
ページ938-941
ページ数4
DOI
出版ステータスPublished - 2007 12 1
イベントISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology - Cairo, Egypt
継続期間: 2007 12 152007 12 18

出版物シリーズ

名前ISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology

Conference

ConferenceISSPIT 2007 - 2007 IEEE International Symposium on Signal Processing and Information Technology
国/地域Egypt
CityCairo
Period07/12/1507/12/18

ASJC Scopus subject areas

  • 計算理論と計算数学
  • コンピュータ ビジョンおよびパターン認識
  • 情報システム
  • 信号処理

フィンガープリント

「A class of prior distributions on context tree models and an efficient algorithm of the Bayes codes assuming it」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル