Properties of jeffreys mixture for markov sources

Jun'Ichi Takeuchi, Tsutomu Kawabata, Andrew R. Barron

研究成果: ジャーナルへの寄稿学術誌査読

8 被引用数 (Scopus)

抄録

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 data compression, where we do not put any restriction on data sequences. Moreover, we give an approximation formula for the prediction probability of Jeffreys mixture for a Markov model. By this formula, it is revealed that the prediction probability by Jeffreys mixture for the Markov model with alphabet {0,1\} is not of the form (nx\s + α)/(ns + β), where nx\s is the number of occurrences of the symbol x following the context s {0,1} and ns = n0\s + n1\s. Moreover, we propose a method to compute our minimax strategy, which is a combination of a Monte Carlo method and the approximation formula, where the former is used for earlier stages in the data, while the latter is used for later stages.

本文言語英語
論文番号6307868
ページ(範囲)438-457
ページ数20
ジャーナルIEEE Transactions on Information Theory
59
1
DOI
出版ステータス出版済み - 2013

!!!All Science Journal Classification (ASJC) codes

  • 情報システム
  • コンピュータ サイエンスの応用
  • 図書館情報学

フィンガープリント

「Properties of jeffreys mixture for markov sources」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