A non-negative expansion for small Jensen-Shannon Divergences

Simple item page
dc.creatorRaj, Anil
dc.creatorWiggins, Chris H.
dc.date2008-10-28
dc.date.accessioned2026-07-07T10:13:42Z
dc.date.available2026-07-07T10:13:42Z
dc.descriptionIn this report, we derive a non-negative series expansion for the Jensen-Shannon divergence (JSD) between two probability distributions. This series expansion is shown to be useful for numerical calculations of the JSD, when the probability distributions are nearly equal, and for which, consequently, small numerical errors dominate evaluation.
dc.description4 page technical report, 2 figures
dc.identifierhttps://arxiv.org/abs/0810.5117
dc.identifierhttp://arxiv.org/abs/0810.5117
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/172622
dc.subjectMachine Learning
dc.titleA non-negative expansion for small Jensen-Shannon Divergences
dc.typetext

Files

Collections

arXiv