A CLASS OF NOISELESS CODES DESIGNED BY DECISION THEORY
スポンサーリンク
概要
- 論文の詳細を見る
The problem of distortionless encoding, when the parameters of the probabilistic model of a source are unknown, is considered from a statistical decision theory point of view. A class of predictive and non-predictive codes are proposed which are optimal within this framework. Specifically, it is shown that the codeword length of the proposed predictive code coincides with that of the proposed non-predictive code for any source sequence. A bound for the redundancy for universal coding at a finite stage is shown the Bayes risk of the proposed codes. If there exists the supremum for the Bayes risk, then there exists a minimax code whose mean code length approaches it in the proposed class of codes, and the minimax code is given by the Bayes solution relative to the prior distribution of the source parameters which maximizes the Bayes risk.
- 横浜商科大学の論文
- 1991-10-15