タイトル | Asymptotics of Bayesian estimation for nested models under misspecification |
---|---|
著者 | 宮 希望 、須子 統太 、安田 豪毅 、松嶋 敏泰 |
年度 | 2012 |
形式 | 国際学会 |
分野 | 情報源符号化 |
掲載雑誌名 | Proceedings of the 2012 International Symposium on Information Theory and its Applications |
掲載号・ページ | pp.86–90, Honolulu, USA |
掲載年 | 2012 |
掲載月 | 10 |
アブスト (日本語) |
学会名:2012 International Symposium on Information Theory and its Applications (ISITA2012) 日程:2012年10月28–31日(発表日: 29日) 場所:Honolulu, USA 査読有 DOI: なし |
アブスト (英語) |
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. |
備考 (日本語) |
1 |
備考 (英語) |
1 |
論文原稿 | |
発表資料 |