Title :
Nonextensive Variational Principles for Rate Distortion Theory and the Information Bottleneck Method
Author :
Venkatesan, R.C.
Author_Institution :
Syst. Res. Corp., Pune
Abstract :
Variational principles for the rate distortion (RD) theory, and the information bottleneck (IB) method, are formulated within the ambit of the generalized nonextensive statistics of Tsallis. Numerical schemes for the nonextensive RD theory and IB method are derived. The physical implications of using nonextensive statistics vis-a-vis Boltzmann-Gibbs statistics are exemplified with the aid of numerical simulations
Keywords :
information theory; statistics; variational techniques; Boltzmann-Gibbs statistics; generalized nonextensive statistics; information bottleneck method; nonextensive variational principles; rate distortion theory; Computational intelligence; Entropy; Information theory; Mathematics; Numerical simulation; Physics; Rate distortion theory; Rate-distortion; Statistical distributions; Statistics;
Conference_Titel :
Foundations of Computational Intelligence, 2007. FOCI 2007. IEEE Symposium on
Conference_Location :
Honolulu, HI
Print_ISBN :
1-4244-0703-6
DOI :
10.1109/FOCI.2007.371520