Title :
On Rate of Convergence of Statistical Estimation of Stationary Ergodic 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 :
Markov processes; approximation theory; estimation theory; Markov approximation; finite alphabets; finite memory processes; n-length realization; stationary ergodic processes; statistical estimation convergence; Conferences; Convergence; Entropy; Hamming distance; Information theory; Markov processes; Mathematics; Random sequences; Stochastic processes; Finite memory estimators; Markov approximation; infinite memory; rate of convergence; stationary ergodic processes; statistical estimation;
Journal_Title :
Information Theory, IEEE Transactions on
DOI :
10.1109/TIT.2010.2050936
