Analysis of adaptive multilevel splitting algorithms in an idealized case
ESAIM: Probability and Statistics, Tome 19 (2015), pp. 361-394.

The Adaptive Multilevel Splitting algorithm [F. Cérou and A. Guyader, Stoch. Anal. Appl. 25 (2007) 417–443] is a very powerful and versatile method to estimate rare events probabilities. It is an iterative procedure on an interacting particle system, where at each step, the k less well-adapted particles among n are killed while k new better adapted particles are resampled according to a conditional law. We analyze the algorithm in the idealized setting of an exact resampling and prove that the estimator of the rare event probability is unbiased whatever k. We also obtain a precise asymptotic expansion for the variance of the estimator and the cost of the algorithm in the large n limit, for a fixed k.

Reçu le :
DOI : 10.1051/ps/2014029
Classification : 65C05, 65C35, 62G30
Mots clés : Monte-Carlo simulation, rare events, multilevel splitting
Bréhier, Charles-Edouard 1, 2 ; Lelièvre, Tony 1 ; Rousset, Mathias 1, 2

1 UniversitéParis-Est, CERMICS (ENPC), INRIA, 6-8 avenue Blaise Pascal, 77455 Marne-la-Vallée, France
2 INRIA Paris-Rocquencourt, Domaine de Voluceau, Rocquencourt, B.P. 105, 78153 Le Chesnay, France
@article{PS_2015__19__361_0,
     author = {Br\'ehier, Charles-Edouard and Leli\`evre, Tony and Rousset, Mathias},
     title = {Analysis of adaptive multilevel splitting algorithms in an idealized case},
     journal = {ESAIM: Probability and Statistics},
     pages = {361--394},
     publisher = {EDP-Sciences},
     volume = {19},
     year = {2015},
     doi = {10.1051/ps/2014029},
     zbl = {1348.65017},
     language = {en},
     url = {http://www.numdam.org/articles/10.1051/ps/2014029/}
}
TY  - JOUR
AU  - Bréhier, Charles-Edouard
AU  - Lelièvre, Tony
AU  - Rousset, Mathias
TI  - Analysis of adaptive multilevel splitting algorithms in an idealized case
JO  - ESAIM: Probability and Statistics
PY  - 2015
SP  - 361
EP  - 394
VL  - 19
PB  - EDP-Sciences
UR  - http://www.numdam.org/articles/10.1051/ps/2014029/
DO  - 10.1051/ps/2014029
LA  - en
ID  - PS_2015__19__361_0
ER  - 
%0 Journal Article
%A Bréhier, Charles-Edouard
%A Lelièvre, Tony
%A Rousset, Mathias
%T Analysis of adaptive multilevel splitting algorithms in an idealized case
%J ESAIM: Probability and Statistics
%D 2015
%P 361-394
%V 19
%I EDP-Sciences
%U http://www.numdam.org/articles/10.1051/ps/2014029/
%R 10.1051/ps/2014029
%G en
%F PS_2015__19__361_0
Bréhier, Charles-Edouard; Lelièvre, Tony; Rousset, Mathias. Analysis of adaptive multilevel splitting algorithms in an idealized case. ESAIM: Probability and Statistics, Tome 19 (2015), pp. 361-394. doi : 10.1051/ps/2014029. http://www.numdam.org/articles/10.1051/ps/2014029/

S. Asmussen and P.W. Glynn, Stochastic Simulation: Algorithms and Analysis. Springer (2007). | Zbl

S.K. Au and J.L. Beck, Estimation of small failure probabilities in high dimensions by subset simulation. J. Probab. Engrg. Mech. 16 (2001) 263–277.

C.E. Bréhier, M. Gazeau, L. Goudenège, T. Lelièvre and M. Rousset, Unbiasedness of some generalized Adaptive Multilevel Splitting algorithms. Preprint (2015). | arXiv

F. Cérou and A. Guyader, Adaptive multilevel splitting for rare event analysis. Stoch. Anal. Appl. 25 (2007) 417–443. | Zbl

F. Cérou and A. Guyader, Adaptive particle techniques and rare event estimation. In Conf. Oxford sur les méthodes de Monte Carlo séquentielles. Vol. 19 of ESAIM Proc. EDP Sciences, Les Ulis (2007) 65–72. | Zbl

F. Cérou, A. Guyader, T. Lelièvre and D. Pommier, A multiple replica approach to simulate reactive trajectories. J. Chem. Phys. 134 (2011) 054108.

F. Cérou, P. Del Moral, T. Furon and A. Guyader, Sequential Monte Carlo for rare event estimation. Stat. Comput. 22 (2012) 795–808. | Zbl

M. Freidlin, Functional integration and partial differential equations. In vol. 109 of Ann. Math. Stud. Princeton University Press, Princeton, NJ (1985). | Zbl

P. Glasserman, P. Heidelberger, P. Shahabuddin and T. Zajic, Multilevel splitting for estimating rare event probabilities. Oper. Res. 47 (1999) 585–600. | Zbl

A. Guyader, N. Hengartner and E. Matzner-Løber, Simulation and estimation of extreme quantiles and extreme probabilities. Appl. Math. Optim. 64 (2011) 171–196. | Zbl

J.M. Hammersley and D.C. Handscomb, Monte Carlo methods. Methuen and Co. Ltd. (1965). | Zbl

H. Kahn and T.E. Harris, Estimation of Particle Transmission by Random Sampling. National Bureau of Standards, Appl. Math. Ser. 12 (1951) 27–30.

G. Rubino and B. Tuffin, Rare Event Simulation using Monte Carlo Methods. Wiley (2009). | Zbl

J. Skilling, Nested Sampling for General Bayesian Computation. Bayesian Anal. 1 (2006) 833–859. | Zbl

Cité par Sources :