A Lower Bound on Arbitrary $f$--Divergences in Terms of the Total Variation

Simple item page
dc.creatorBröcker, Jochen
dc.date2009-03-10
dc.date.accessioned2026-07-07T12:50:53Z
dc.date.available2026-07-07T12:50:53Z
dc.descriptionAn important tool to quantify the likeness of two probability measures are f-divergences, which have seen widespread application in statistics and information theory. An example is the total variation, which plays an exceptional role among the f-divergences. It is shown that every f-divergence is bounded from below by a monotonous function of the total variation. Under appropriate regularity conditions, this function is shown to be monotonous. Remark: The proof of the main proposition is relatively easy, whence it is highly likely that the result is known. The author would be very grateful for any information regarding references or related work.
dc.description4 pages
dc.identifierhttps://arxiv.org/abs/0903.1765
dc.identifierhttp://arxiv.org/abs/0903.1765
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/222822
dc.subjectProbability
dc.subjectInformation Theory
dc.subjectStatistics Theory
dc.titleA Lower Bound on Arbitrary $f$--Divergences in Terms of the Total Variation
dc.typetext

Files

Collections

arXiv