On Relations Between Tight Bounds for Symmetric f-Divergences and Binary Divergences

2022/10/18 by Nishiyama, Tomohiro
#FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2210.09571

Abstract

Minimizing divergence measures under a constraint is an important problem. We derive a sufficient condition that binary divergence measures provide lower bounds for symmetric divergence measures under a given triangular discrimination or given means and variances. Assuming this sufficient condition, the former bounds are always tight, and the latter bounds are tight when two probability measures have the same variance. An application of these results for nonequilibrium physics is provided.

Related

• Inequalities Among Symmetric Divergence Measures and Their Refinement
• Sharp Inequalities for f-divergences
• Bounds on Non-Symmetric Divergence Measures in Terms of Symmetric Divergence Measures
• Generalized Symmetric Divergence Measures and Inequalities
• A Sequence of Inequalities among Difference of Symmetric Divergence Measures