タイトル | Asymptotics of Bayesian Inference for a Class of Probabilistic Models under Misspecification |
---|---|
著者 | 宮 希望 、須子 統太 、安田 豪毅 、松嶋 敏泰 |
年度 | 2014 |
形式 | 論文誌 |
分野 | 情報源符号化 |
掲載雑誌名 | IEICE Trans. Fundamentals |
掲載号・ページ | vol.E97-A, no.12, pp.2352–2360 |
掲載年 | 2014 |
掲載月 | 12 |
アブスト (日本語) |
査読有 DOI: 10.1587/transfun.E97.A.2352 |
アブスト (英語) |
In this paper, sequential prediction is studied. The typical assumptions about the probabilistic model in sequential prediction are following two cases. One is the case that a certain probabilistic model is given and the parameters are unknown. The other is the case that not a certain probabilistic model but a class of probabilistic models is given and the parameters are unknown. If there exist some parameters and some models such that the distributions that are identified by them equal the source distribution, an assumed model or a class of models can represent the source distribution. This case is called that specifiable condition is satisfied. In this study, the decision based on the Bayesian principle is made for a class of probabilistic models (not for a certain probabilistic model). The case that specifiable condition is not satisfied is studied. Then, the asymptotic behaviors of the cumulative logarithmic loss for individual sequence in the sense of almost sure convergence and the expected loss, i.e. redundancy are analyzed and the constant terms of the asymptotic equations are identified. |
備考 (日本語) |
3 |
備考 (英語) |
3 |
論文原稿 | |
発表資料 |
関連論文
- A New Latent Class Model for Analysis of Purchasing and Browsing Histories on EC Sites
- Linear Programming Decoding of Binary Linear Codes for Symbol-Pair Read Channels
- A Heuristic Search Method with the Reduced List of Test Error Patterns for Maximum Likelihood Decoding
- Parallel Architecture for Generalized LFSR in LSI Built-In Self Testing
- Parallel Encoder and Decoder Architecture for Cyclic Codes
- A Generalization of B.S.Clarke and A.R.Barron's Asymptotics of Bayes Codes for FSMX Sources
- Almost Sure and Mean Convergence of Extended Stochastic Complexity
- A Source Model with Probability Distribution over Word Set and Recurrence Time Theorem
- Properties of a Word-Valued Source with a Non-prefix-free Word Set
- An Analysis of Slepian-Wolf Coding Problem Based on the Asymptotic Normality
- On the Overflow Probability of Fixed - to - Variable Length Codes with Side Information
- A Study on the Degrees of Freedom in an Experimental Design Model Based on an Orthonormal System
- A Note on Relation between the Fourier Coefficients and the Effects in the Experimental Design
- Asymptotic property of universal lossless coding for independent piecewise identically distributed sources
- A Note on the Linear Programming Decoding of Binary Linear Codes for Multiple-Access Channel
- A Note on Automatic Construction Algorithms for Orthogonal Designs of Experiments Using Error-correcting Codes
- A Note on the Branch-and-Cut Approach to Decoding Linear Block Codes
- Estimation of the Effects in the Experimental Design using Fourier Transforms
- A Note on a Sampling Theorem for Functions over $GF(q)^n$ Domain
- On Precise Achievable Conditions in Resolvability Problem Based on the Asymptotic Normality