Computer Science – Information Theory
Scientific paper
2011-02-24
Computer Science
Information Theory
7 pages, Prop. 5 modified, in Proceedings of the 2011 IEEE International Symposium on Information Theory
Scientific paper
This paper extends some geometric properties of a one-parameter family of relative entropies. These arise as redundancies when cumulants of compressed lengths are considered instead of expected compressed lengths. These parametric relative entropies are a generalization of the Kullback-Leibler divergence. They satisfy the Pythagorean property and behave like squared distances. This property, which was known for finite alphabet spaces, is now extended for general measure spaces. Existence of projections onto convex and certain closed sets is also established. Our results may have applications in the R\'enyi entropy maximization rule of statistical physics.
Ashok Kumar M.
Sundaresan Rajesh
No associations
LandOfFree
Further Results on Geometric Properties of a Family of Relative Entropies does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Further Results on Geometric Properties of a Family of Relative Entropies, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Further Results on Geometric Properties of a Family of Relative Entropies will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-86284