Title :
Lower bounds on expected redundancy
Author_Institution :
Dept. of Stat., California Univ., Berkeley, CA, USA
Abstract :
This paper focuses on lower bound results on expected redundancy for universal compression of i.i.d. data from parametric and nonparametric families. Two types of lower bounds are reviewed. One is Rissanen´s almost pointwise lower bound and its extension to the nonparametric case. The other is minimax lower bounds, for which a new proof is given in the nonparametric case
Keywords :
data compression; minimax techniques; redundancy; stochastic processes; IID data; Rissanen´s lower bound; expected redundancy; lower bounds; minimax lower bounds; nonparametric families; parametric families; universal compression; Estimation error; Hypercubes; Minimax techniques; Mutual information; Parametric statistics; Redundancy; Stochastic processes;
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.1994.513857
