Computer Science – Information Theory
Scientific paper
2009-11-10
Computer Science
Information Theory
1+4 pages, no figures
Scientific paper
It is shown that the $f$-divergence between two probability measures $P$ and $R$ equals the supremum of the same $f$-divergence computed over all finite measurable partitions of the original space, thus generalizing results previously proved by Gel'fand and Yaglom and by Peres for the Information Divergence and more recently by Dukkipati, Bhatnagar and Murty for the Tsallis' and Renyi's divergences.
No associations
LandOfFree
On a Gel'fand-Yaglom-Peres theorem for f-divergences 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 On a Gel'fand-Yaglom-Peres theorem for f-divergences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On a Gel'fand-Yaglom-Peres theorem for f-divergences will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-51654