Almost sure and mean convergence of extended stochastic complexity

Masayuki Gotoh*, Toshiyasu Matsushima, Shigeichi Hirasawa

*この研究の対応する著者

研究成果: Article査読

1 被引用数 (Scopus)

抄録

We analyze the extended stochastic complexity (ESC) which has been proposed by K. Yamanishi. The ESC can be applied to learning algorithms for on-line prediction and batch-learning settings. Yamanishi derived the upper bound of ESC satisfying uniformly for all data sequences and that of the asymptotic expectation of ESC. However, Yamanishi concentrates mainly on the worst case performance and the lower bound has not been derived. In this paper, we show some interesting properties of ESC which are similar to Bayesian statistics: the Bayes rule and the asymptotic normality. We then derive the asymptotic formula of ESC in the meaning of almost sure and mean convergence within an error of o(1) using these properties.

本文言語English
ページ(範囲)2129-2134
ページ数6
ジャーナルIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
E82-A
10
出版ステータスPublished - 1999 1 1

ASJC Scopus subject areas

  • 信号処理
  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • 電子工学および電気工学
  • 応用数学

フィンガープリント

「Almost sure and mean convergence of extended stochastic complexity」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