DocumentCode
2519983
Title
Computation of Csiszár’s mutual Information of order α
Author
Karakos, Damianos ; Khudanpur, Sanjeev ; Priebe, Carey E.
Author_Institution
Dept. of Electr. & Comput. Eng., Center for Language & Speech Process., Baltimore, MD
fYear
2008
fDate
6-11 July 2008
Firstpage
2106
Lastpage
2110
Abstract
Csiszar introduced the mutual information of order alpha in [1] as a parameterized version of Shannon´s mutual information. It involves a minimization over the probability space, and it cannot be computed in closed form. An alternating minimization algorithm for its computation is presented in this paper, along with a proof of its convergence. Furthermore, it is proved that the algorithm is an instance of the Csiszar-Tusnady iterative minimization procedure [2].
Keywords
minimisation; probability; Shannon mutual information; iterative minimization procedure; minimization algorithm; mutual information; probability space; Clustering algorithms; Distributed computing; Iterative algorithms; Mathematics; Minimization methods; Mutual information; Natural languages; Random variables; Speech processing; Statistics;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Theory, 2008. ISIT 2008. IEEE International Symposium on
Conference_Location
Toronto, ON
Print_ISBN
978-1-4244-2256-2
Electronic_ISBN
978-1-4244-2257-9
Type
conf
DOI
10.1109/ISIT.2008.4595361
Filename
4595361
Link To Document