Details

Autor(en) / Beteiligte

• Marton, K.

Titel

Bounding d̄-Distance by Informational Divergence: A Method to Prove Measure Concentration

Ist Teil von

• The Annals of probability, 1996-04, Vol.24 (2), p.857-866

Ort / Verlag

Hayward, CA: Institute of Mathematical Statistics

Erscheinungsjahr

1996

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• There is a simple inequality by Pinsker between variational distance and informational divergence of probability measures defined on arbitrary probability spaces. We shall consider probability measures on sequences taken from countable alphabets, and derive, from Pinsker's inequality, bounds on the d̄-distance by informational divergence. Such bounds can be used to prove the "concentration of measure" phenomenon for some nonproduct distributions.