On Pairs of f-divergences and their Joint Range

2010/07/01 by Peter Harremoës, Harremoës, Peter, Igor Vajda +1 · 4 citations
Computer Science · Mathematics · #26Dxx #94A17 #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Statistics Theory (math.ST) #cs.IT #math.IT #math.ST #msc:26Dxx #msc:94A17 #stat.TH

paper · pdf · doi:10.48550/arxiv.1007.0097

7 pages, 4 figures

arxiv created 2010/07/01 · arxiv updated 2010/07/02

Abstract

We compare two f-divergences and prove that their joint range is the convex hull of the joint range for distributions supported on only two points. Some applications of this result are given.

Cited by

• Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergences
• Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation Learning
• On Convex Functions of Gaussian Variables
• Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)

Related

• Joint Range of f-divergences
• On the mixed f-divergence for multiple pairs of measures
• Sharp Inequalities for f-divergences
• Mixed f-divergence for multiple pairs of measures
• Monotonically Decreasing Sequence of Divergences