Title :
Jeffreys´ prior yields the asymptotic minimax redundancy
Author :
Clarke, Bertrand S. ; Barron, Andrew R.
Author_Institution :
Dept. of Stat., British Columbia Univ., Vancouver, BC, Canada
Abstract :
We determine the asymptotic minimax redundancy of universal data compression in a parametric setting and show that it corresponds to the use of Jeffreys prior. Statistically, this formulation of the coding problem can be interpreted in a prior selection context and in an estimation context
Keywords :
estimation theory; minimax techniques; redundancy; source coding; statistical analysis; Jeffreys´ prior; asymptotic minimax redundancy; coding problem; estimation context; parametric setting; source coding; universal data compression; Channel coding; Data compression; Entropy; Game theory; Maximum likelihood decoding; Maximum likelihood estimation; Minimax techniques; Mutual information; Source coding; Statistical distributions;
Conference_Titel :
Information Theory and Statistics, 1994. Proceedings., 1994 IEEE-IMS Workshop on
Conference_Location :
Alexandria, VA
Print_ISBN :
0-7803-2761-6
DOI :
10.1109/WITS.1994.513856
