Title :
On convergence rates of finite memory estimators of infinite memory processes
Author :
Csiszár, Imre ; Talata, Zsolt
Author_Institution :
Alfred Renyi Inst. of Math., Hungarian Acad. of Sci., Budapest, Hungary
Abstract :
Stationary ergodic processes with finite alphabets are approximated by finite memory processes based on an n-length realization of the process. Under the assumptions of summable continuity rate and non-nullness, a rate of convergence in d̅-distance is obtained, with explicit constants. Asymptotically, as n → ∞, the result is near the optimum.
Keywords :
stochastic processes; convergence rates; finite memory estimators; infinite memory processes; stationary ergodic processes; Convergence; Entropy; Hamming distance; Markov processes; Mathematics; Random sequences; Stochastic processes;
Conference_Titel :
Information Theory (ITW 2010, Cairo), 2010 IEEE Information Theory Workshop on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-6372-5
DOI :
10.1109/ITWKSPS.2010.5503181