Quantitative concentration inequalities on sample path space for mean field interaction

François Bolley

ESAIM: Probability and Statistics (2010)

  • Volume: 14, page 192-209
  • ISSN: 1292-8100

Abstract

top
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.

How to cite

top

Bolley, François. "Quantitative concentration inequalities on sample path space for mean field interaction." ESAIM: Probability and Statistics 14 (2010): 192-209. <http://eudml.org/doc/250821>.

@article{Bolley2010,
abstract = { 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. },
author = {Bolley, François},
journal = {ESAIM: Probability and Statistics},
keywords = {Mean field limits; particle approximation; transportation inequalities; mean field limits},
language = {eng},
month = {7},
pages = {192-209},
publisher = {EDP Sciences},
title = {Quantitative concentration inequalities on sample path space for mean field interaction},
url = {http://eudml.org/doc/250821},
volume = {14},
year = {2010},
}

TY - JOUR
AU - Bolley, François
TI - Quantitative concentration inequalities on sample path space for mean field interaction
JO - ESAIM: Probability and Statistics
DA - 2010/7//
PB - EDP Sciences
VL - 14
SP - 192
EP - 209
AB - 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.
LA - eng
KW - Mean field limits; particle approximation; transportation inequalities; mean field limits
UR - http://eudml.org/doc/250821
ER -

References

top
  1. S. Benachour, B. Roynette, D. Talay and P. Vallois, Nonlinear self-stabilizing processes. I: Existence, invariant probability, propagation of chaos. Stoch. Proc. Appl.75 (1998) 173–201.  
  2. D. Benedetto, E. Caglioti, J.A. Carrillo and M. Pulvirenti, A non-Maxwellian steady distribution for one-dimensional granular media. J. Statist. Phys.91 (1998) 979–990.  
  3. S. Bobkov and F. Götze, Exponential integrability and transportation cost related to logarithmic Sobolev inequalities. J. Funct. Anal. 163 (1999) 1–28.  
  4. F. Bolley, Quantitative concentration inequalities on sample path space for mean field interaction. Available online at www.ceremade.dauphine.fr/~bolley (2008).  
  5. F. Bolley and C. Villani, Weighted Csiszár-Kullback-Pinsker inequalities and applications to transportation inequalities. Ann. Fac. Sci. Toulouse Math.6 (2005) 331–352.  
  6. F. Bolley, A. Guillin and C. Villani, Quantitative concentration inequalities for empirical measures on non-compact spaces. Probab. Theory Relat. Fields137 (2007) 541–593.  
  7. J.A. Carrillo, R.J. McCann and C. Villani, Contractions in the 2-Wasserstein length space and thermalization of granular media. Arch. Rat. Mech. Anal.179 (2006) 217–263.  
  8. P. Cattiaux, A. Guillin and F. Malrieu, Probabilistic approach for granular media equations in the non uniformly case. Probab. Theory Relat. Fields140 (2008) 19–40.  
  9. A. Dembo and O. Zeitouni, Large deviations techniques and applications. Springer, NewYork (1998).  
  10. H. Djellout, A. Guillin and L. Wu, Transportation cost-information inequalities and applications to random dynamical systems and diffusions. Ann. Probab.32 (2004) 2702–2732.  
  11. J. Dolbeault, Free energy and solutions of the Vlasov-Poisson-Fokker-Planck system: external potential and confinement (large time behavior and steady states). J. Math. Pures Appl.9 (1999) 121–157.  
  12. X. Fernique, Régularité des trajectoires des fonctions aléatoires gaussiennes. Lect. Notes Math. 480. Springer, Berlin (1975).  
  13. N. Gozlan, Principe conditionnel de Gibbs pour des contraintes fines approchées et inégalités de transport. Thèse de doctorat de l'Université de Paris 10-Nanterre, 2005).  
  14. S.R. Kulkarni and O. Zeitouni, A general classification rule for probability measures. Ann. Statist.23 (1995) 1393–1407.  
  15. G.G. Lorentz, Approximation of functions. Holt, Rinehart and Winston, New York (1966).  
  16. F. Malrieu, Logarithmic Sobolev inequalities for some nonlinear PDE's. Stoch. Proc. Appl.95 (2001) 109–132.  
  17. S. Méléard, Asymptotic behaviour of some interacting particle systems; McKean-Vlasov and Boltzmann models. Lect. Notes Math. 1627. Springer, Berlin (1996).  
  18. A.-S. Sznitman, Topics in propagation of chaos. Lect. Notes Math. 1464. Springer, Berlin (1991).  
  19. A. van der Vaart and J. Wellner, Weak convergence and empirical processes. Springer, Berlin (1995).  
  20. C. Villani, Topics in optimal transportation, volume 58 of Grad. Stud. Math. A.M.S., Providence (2003).  

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.