Program: BIG'MC
Issues in large scale Monte Carlo

Coordinator of the project : Gersende FORT

Local coordinators : Christian ROBERT and Benjamin JOURDAIN

Institut TELECOM Université Dauphine, Laboratoire CEREMADE ENPC - Université Paris Est, Laboratoire CERMICS
Olivier CAPPE Nicolas CHOPIN Aurélien ALFONSI
Gersende FORT Jean-Michel MARIN Jean-François DELMAS



Post-Doc Position :           Convergence of adaptive MCMC methods
Summary Adaptive Markov Chain Monte Carlo (MCMC) methods are currently a very active field of research. MCMC methods are sampling methods, based on Markov Chains which are ergodic with respect to the target probability measure. The principle of adaptive methods is to optimize on the fly some design parameters of the algorithm with respect to a given criterion reflecting the sampler's performance (optimize the acceptance rate, optimize an importance sampling function, etc...).
A postdoctoral position is opened to work on the numerical analysis of adaptive MCMC methods: convergence, numerical efficiency, development and analysis of new algorithms.  A particular emphasis will be given to applications in statistics and molecular dynamics.  (Detailed description)

Position funded by the French National Research Agency (ANR) through the 2009-2012 project ANR-08-BLAN-0218.

Required diploma
   PhD thesis in  statistics orprobability, with a competitive track record.
Required skills  experience in MCMC methods and their mathematical analysis.  
Deadline for applications :  September 2010.

Applications must include :
a detailed CV with a description of realized projects
a motivation letter
a summary of the thesis
2 or 3 recommendation letters
preferred starting dates and duration

and must be sent to Gersende FORT ( in pdf format; or by standard mail to :    Gersende FORT (LTCI, 46 rue Barrault, 75 634 Paris Cedex 13, Paris, France).
Duration : 12 months.
Location :  Paris. The position will benefit from  an  interdisciplinary environment involving numerical analysts, statisticians and probabilists, and of strong interactions between the partners of the project ANR-08-BLAN-0218

    Meeting of the project :  December, 4 2008, at TELECOM ParisTech
    Seminar : January, 29 ; March, 12 ; April, 30 ; June, 4 ; June, 25 ; October, 22; November 26 : at IHP  see the webpage of the seminar
Meeting of the project : September, 24 .
    Seminar : January, 28; February, 18; March, 25; April, 15; May, 27;  Juin, 10; Ocotber 7; November 18 : 
at IHP  see the webpage of the seminar
    Seminar : January, 6; February, 3; March, 3;  April, 7;  May, 5; June, 9;  September, 1st;  October, 13;  November, 15;  December, 8 : at IHP, see the webpage of the
    Meeting of the project : October, 13.

Seminar : every month, at IHP. [see the webpage]
Course : "Méthodes de Monte Carlo par Chaînes de Markov adaptatives" organized  by ENPC &Univ. Paris-Est. Invited : Y. ATCHADE (Univ. Michigan, USA), June 2010, Paris, France.
International Conference
3rd Conference on numerical methods in finance, organized by ENPC, April 15-17 2009,  Paris, France.

Satellite meeting "Adaptive Monte Carlo methods" of the MCMCski conference, organized by C.P. ROBERT (Univ. Dauphine),
Jan 3-4 2011, Snowbird, Utah.
Special session "
Monte Carlo methods for Bayesian inverse problems " of the ASMDA 2011 conference, organized by G. FORT (LTCI), June 2011, Roma, Italy.
Satellite meeting of the conference "Méthodes particulaires pour les modèles de diffusion", organized by C.P.  ROBERT (Univ. Dauphine), July 2011, Barcelona, Spain.

Workshop "Confronting intractability in Statistical Inference"
, April 16-19 2012 Bristol, UK. With invited speakers C.P. ROBERT (Univ. Dauphine) and N. CHOPIN (CREST).
Workshop "Advances in Markov chain Monte Carlo", April 23-25 2012, Edinburgh, UK. Organized by C.P. ROBERT (Univ. Dauphine).
Conference ISBA 2012, June 2012, Kyoto, Japan. Invited sessions and Special topic sessions organized by J. ROUSSEAU (Univ. Dauphine) and C.PO. ROBERT (Univ. Dauphine)

Y. Atchadé, G. Fort, E. Moulines, P. Priouret. Adaptive MCMC : theory and methods, submitted.
J.M. Cornuet,  J.M. Marin, A. Mira, C.P. Robert.  Adaptive Multiple Importance Sampling, ArXiv:0907.1254
R. Douc, C.P. Robert. A vanilla Rao-Blackwellisation of Metropolis-Hastings algorithms, ArXiv:0904.2144
B. Jourdain, J. Lelong.  Robust adaptive  Importance Sampling for Normal Random vectors, To appear in Ann. Appl. Prob., [preprint]
B. Jourdain, T. Lelièvre, R. Roux. Existence, uniqueness and convergence of a particle approximation for the Adaptive Biasing Force process; ArXiv:0903.4518