Asymptotics of Bayesian estimation for nested models under misspecification

研究成果: Conference contribution

抜粋

We analyze the asymptotic properties of the cumulative logarithmic loss in the decision problem based on the Bayesian principle and explicitly identify the constant terms of the asymptotic equations as in the case of previous studies by Clarke and Barron and Gotoh et al. We assume that the set of models is given that identify a class of parameterized distributions, it has a nested structure and the source distribution is not contained in all the families of parameterized distributions that are identified by each model. The cumulative logarithmic loss is the sum of the logarithmic loss functions for each time decision -, e.g., the redundancy in the universal noiseless source coding.

元の言語English
ホスト出版物のタイトル2012 International Symposium on Information Theory and Its Applications, ISITA 2012
ページ86-90
ページ数5
出版物ステータスPublished - 2012 12 1
イベント2012 International Symposium on Information Theory and Its Applications, ISITA 2012 - Honolulu, HI, United States
継続期間: 2012 10 282012 10 31

出版物シリーズ

名前2012 International Symposium on Information Theory and Its Applications, ISITA 2012

Conference

Conference2012 International Symposium on Information Theory and Its Applications, ISITA 2012
United States
Honolulu, HI
期間12/10/2812/10/31

    フィンガープリント

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

これを引用

Miya, N., Suko, T., Yasuda, G., & Matsushima, T. (2012). Asymptotics of Bayesian estimation for nested models under misspecification. : 2012 International Symposium on Information Theory and Its Applications, ISITA 2012 (pp. 86-90). [6401057] (2012 International Symposium on Information Theory and Its Applications, ISITA 2012).