On McDiarmid's concentration inequality

In this paper we improve the rate function in the McDiarmid concentration inequality for separately Lipschitz functions of independent random variables. In particular the rate function tends to infinity at the boundary. We also prove that in some cases the usual normalization factor is not adequate and may be improved.

Data and Resources

Additional Info

Field Value
Source https://hal.science/hal-00798275
Author Rio, Emmanuel
Maintainer CCSD
Last Updated May 13, 2026, 07:08 (UTC)
Created May 13, 2026, 07:08 (UTC)
Identifier hal-00798275
Language en
Rights https://about.hal.science/hal-authorisation-v1/
contributor Laboratoire de Mathématiques de Versailles (LMV) ; Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)
creator Rio, Emmanuel
date 2013-03-06T00:00:00
harvest_object_id 12f3b0b3-17a9-4f10-9a84-cc111851d41a
harvest_source_id 3374d638-d20b-4672-ba96-a23232d55657
harvest_source_title test moissonnage SELUNE
metadata_modified 2024-07-16T00:00:00
set_spec type:UNDEFINED