Shuai FU

Post-doc researcher at IDSIA

• Imprecise Probability Group
• Istituto "Dalle Molle" di Studi sull'Intelligenza Artificiale (IDSIA)


Address :

• Istituto "Dalle Molle" di Studi sull'Intelligenza Artificiale (IDSIA)
  Galleria 2
  CH-6928 Manno (Lugano), Switzerland
  
  
Electronic mail :
• shuai at idsia.ch
  

Tel :
• +41 58 666 6509

About myself ...

I have started my post-doc research at IDSIA since january 2013, which explores iterated time series predictions within hierarchical structures. Before arriving at Switzerland, I finished my Ph.D thesis at University of Paris 11 on 14 december 2012, with subject "Bayesian probablilistic inversion in uncertainty analysis", advised by Professer Gilles Celeux within team SELECT, INRIA Saclay, equally within department MRI (Industrial Risk Management) EDF R&D. guided by Mathieu Couplet and Nicolas Bousquet.

Before my Ph.D studies, I got my master degree in Financial Mathematics (advised by Nicole El Karoui) at University of Paris 6, in cooperation with Ecole Polytechnique, and my dual bachelor degrees in Applicated Mathematics at University of Lille 1 and Harbin Institute of Technology in China.


Research activities

Main interests :

• Bayesian statistics and MCMC algorithms
• Inverse problems, uncertainty analysis
  
• Design of experiments / Adaptive kriging method
• Time series prediction / Hierarchical time series
  
• Econometrics, Risk analysis
• Quantitative methods for pricing and hedging derivatives

Conferences and workshops :

• An adaptive kriging method for characterizing uncertainty in inverse problems. 58th ISI Congress, Dublin, Ireland (08. 2011) [abstract]
• A Bayesian solution to characterizing uncertainty in inverse problems. IMS-China International conference on Statistics and Probability, Xi'an, China (07. 2011)
• A Bayesian solution to characterizing uncertainty in inverse problems. GdR MASCOT-NUM, Villard de Lans (03. 2011) [abstract] [slides]
• Inversion probabiliste en analyse d'incertitude. Séminaire Animation S&T de la compétence APSPP, EDF R&D, Chatou (12. 2010)
• Estimation de modèles markoviens discrets dans un cadre industriel fiabiliste à données manquantes. Journée WP2.1, Supelec, Paris (11. 2010)
• Problème inverse statistique dans des modèles de crues. Traitement par un algorithme EM et par une méthodologie bayésienne. Journée modèles inverses, SFdS, Paris (09. 2010)
• Estimation de modèles markoviens discrets dans un cadre industriel fiabiliste à données manquantes. SFdS congress, Marseille (05. 2010) [abstract]

Research and conference papers:

• Fu, S., Couplet, M. and Bousquet, N. (2012)
  An adaptive kriging method for characterizing uncertainty in inverse problems (in preparation)
  
• Fu, S., Celeux, G., Bousquet, N. and Couplet, M. (2012)
  Bayesian inference for inverse problems occuring in uncertainty analysis
  Technical report, Rapport de recherche INRIA (hal)
• Pasanisi, A., Fu, S. and Bousquet, N. (2012)
  Estimating discrete Markov models from various incomplete data schemes
  Computational Statistics & Data Analysis, Volume 56, Issue 9 (online)
• Fu, S., Couplet, M. and Bousquet, N. (2011)
  An adaptive kriging method for characterizing uncertainty in inverse problems
  ISI congress, Special Topics Session, Dublin, Ireland (online)
• Pasanisi, A., Fu, S. and Bousquet, N. (2010)
  Estimation de modèles markoviens discrets dans un cadre industriel fiabiliste à données manquantes
  SFdS congress, Marseille, France (online)

Awards and honors :

• "Distinguished students studying abroad" award, from China Scholarship Council (2012)
• "My fruitful year 2012 in France" - interview with Journal of Weifang, China (2012)
  

Exams of Finance :

• Level I of CFA program (Chartered Financial Analyst) passed (2011)

Teaching activities

• Faculté Jean Monnet, Université Paris-Sud 11, 2010-2012
  TD of Probabilities and Statistics, Bachelor 2, Economies gestion

Other links

• My detailed CV