Relative Information Loss - An Introduction
Information Theory
2012-04-02 v1 math.IT
Abstract
We introduce a relative variant of information loss to characterize the behavior of deterministic input-output systems. We show that the relative loss is closely related to Renyi's information dimension. We provide an upper bound for continuous input random variables and an exact result for a class of functions (comprising quantizers) with infinite absolute information loss. A connection between relative information loss and reconstruction error is investigated.
Cite
@article{arxiv.1203.6791,
title = {Relative Information Loss - An Introduction},
author = {Bernhard C. Geiger and Gernot Kubin},
journal= {arXiv preprint arXiv:1203.6791},
year = {2012}
}
Comments
6 pages; submitted to a conference