Quantitative concentration inequalities on sample path space for mean field interaction

Abstract

We consider a system of particles experiencing diffusion and mean field interaction, and study its behaviour when the number of particles goes to infinity. We derive non-asymptotic large deviation bounds measuring the concentration of the empirical measure of the paths of the particles around its limit. The method is based on a coupling argument, strong integrability estimates on the paths in Holder norm, and some general concentration result for the empirical measure of identically distributed independent paths.

References in corpus (2)

• Transportation cost-information inequalities and applications to random dynamical systems and diffusions
• Quantitative concentration inequalities for empirical measures on non-compact spaces