Universal Interior Optimality of Jensen-Shannon Divergence Contraction Coefficients for Binary-Input Channels

We prove that the contraction coefficient for Jensen-Shannon divergence (JSD) achieves its supremum in the interior of the probability simplex, not at the vertices. This contradicts the long-standing folklore assumption that extremal behavior for f-divergences occurs at simplex vertices.

Keywords

Jensen-Shannon divergence, binary channels, Dobrushin theorem, contraction coefficient, f-divergence, strong data processing inequality, information theory

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

0

Average

Green