Generalized Statistics Framework for Rate Distortion Theory with Bregman Divergences
Statistical Mechanics
2007-07-13 v3 Information Theory
math.IT
Abstract
A variational principle for the rate distortion (RD) theory with Bregman divergences is formulated within the ambit of the generalized (nonextensive) statistics of Tsallis. The Tsallis-Bregman RD lower bound is established. Alternate minimization schemes for the generalized Bregman RD (GBRD) theory are derived. A computational strategy to implement the GBRD model is presented. The efficacy of the GBRD model is exemplified with the aid of numerical simulations.
Cite
@article{arxiv.cond-mat/0701218,
title = {Generalized Statistics Framework for Rate Distortion Theory with Bregman Divergences},
author = {R. C. Venkatesan},
journal= {arXiv preprint arXiv:cond-mat/0701218},
year = {2007}
}
Comments
5 pages + 2 figures. Typos corrected