Title :
Universal estimation of directed information
Author :
Zhao, Lei ; Permuter, Haim ; Kim, Young-Han ; Weissman, Tsachy
Author_Institution :
Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
Abstract :
In this paper, we develop a universal algorithm to estimate Massey´s directed information for stationary ergodic processes. The sequential probability assignment induced by a universal source code plays the critical role in the estimation. In particular, we use context tree weighting to implement the algorithm. Some numerical results are provided to illustrate the performance of the proposed algorithm.
Keywords :
probability; sequential estimation; source coding; Massey directed information estimation; context tree weighting; sequential probability assignment; stationary ergodic process; universal estimation algorithm; universal source code; Channel capacity; Channel coding; Entropy; Mutual information; Output feedback; Portfolios; Random variables; Sequences; Source coding; Testing;
Conference_Titel :
Information Theory Proceedings (ISIT), 2010 IEEE International Symposium on
Conference_Location :
Austin, TX
Print_ISBN :
978-1-4244-7890-3
Electronic_ISBN :
978-1-4244-7891-0
DOI :
10.1109/ISIT.2010.5513624
