Quantitative concentration inequalities on sample path space for mean field interaction
ESAIM: Probability and Statistics, Tome 14 (2010), pp. 192-209
We consider the approximation of a mean field stochastic process by a large interacting particle system. We derive non-asymptotic large deviation bounds measuring the concentration of the empirical measure of the paths of the particles around the law of the process. The method is based on a coupling argument, strong integrability estimates on the paths in Hölder norm, and a general concentration result for the empirical measure of identically distributed independent paths.
DOI :
10.1051/ps:2008033
Classification :
82C22, 35K55, 90C08
Keywords: mean field limits, particle approximation, transportation inequalities
Keywords: mean field limits, particle approximation, transportation inequalities
@article{PS_2010__14__192_0,
author = {Bolley, Fran\c{c}ois},
title = {Quantitative concentration inequalities on sample path space for mean field interaction},
journal = {ESAIM: Probability and Statistics},
pages = {192--209},
year = {2010},
publisher = {EDP-Sciences},
volume = {14},
doi = {10.1051/ps:2008033},
mrnumber = {2741965},
language = {en},
url = {http://geodesic.mathdoc.fr/articles/10.1051/ps:2008033/}
}
TY - JOUR AU - Bolley, François TI - Quantitative concentration inequalities on sample path space for mean field interaction JO - ESAIM: Probability and Statistics PY - 2010 SP - 192 EP - 209 VL - 14 PB - EDP-Sciences UR - http://geodesic.mathdoc.fr/articles/10.1051/ps:2008033/ DO - 10.1051/ps:2008033 LA - en ID - PS_2010__14__192_0 ER -
%0 Journal Article %A Bolley, François %T Quantitative concentration inequalities on sample path space for mean field interaction %J ESAIM: Probability and Statistics %D 2010 %P 192-209 %V 14 %I EDP-Sciences %U http://geodesic.mathdoc.fr/articles/10.1051/ps:2008033/ %R 10.1051/ps:2008033 %G en %F PS_2010__14__192_0
Bolley, François. Quantitative concentration inequalities on sample path space for mean field interaction. ESAIM: Probability and Statistics, Tome 14 (2010), pp. 192-209. doi: 10.1051/ps:2008033
Cité par Sources :
