The ReDICE Consortium


ReDICE was a research project (2011-2015) gathering industry and academia partners around innovative mathematical methods for the design and analysis of computer experiments.


  • UNIBE (University of Bern): Academic partner and project coordinator
  • EMSE (École Nationale Supérieure des Mines de Saint-Étienne): Academic partner
  • INRIA (Institut National de Recherche en Informatique et Automatique): Academic and project administration partner
  • IRSN (Institut de Radioprotection et de Sûreté Nucléaire): Industry partner
  • EDF R&D (Électricité de France): Industry partner
  • Renault: Industry partner
  • CEA (Commissariat à l'Énergie Atomique): Industry partner
  • IFPen (IFP Énergies Nouvelles): Industry partner
  • IMT (Institut de Mathématiques de Toulouse): Scientific expertise
  • UNICE (Université de Nice): Scientific expertise
  • Alpestat : Software expertise

Main research topics

  • Metamodel-based optimization, inversion, and related strategies
  • Multi-fidelity metamodels and mixtures of metamodels
  • Computer experiments involving functional data
  • Special kernels and designs

Co-funded and associated Ph.D. theses

  • François Bachoc (2010-2013): Parametric estimation of covariance function in Gaussian-process based Kriging models.
    Application to uncertainty quantification for computer models (associated to ReDICE through CEA).
  • Mickaël Binois (2013-): High-dimensional multi-objective optimization for automotive design (Cifre Ph.D. with Renault as industrial party).
  • Clément Chevalier (2010-2013): Fast uncertainty reduction strategies relying on Gaussian process models (Ph.D. funded by IRSN and ReDICE).
  • Loïc Le Gratiet (2010-2013) : Multi-fidelity Gaussian process regression for computer experiments (associated to ReDICE through CEA).
  • Hassan Maatouk (2012-) : Spectral methods and non-stationary kernels in computer experiments (associated to ReDICE through EMSE and IRSN).
  • Sébastien Marmin (2014-) : Multiscale non-stationary Gaussian process models for adaptive design (associated to ReDICE through IRSN and UniBE).
  • Federico Zertuche (2011-) : New multi-fidelity kriging metamodels (Université Joseph Fourier Ph.D. co-sponsored by ReDICE).

Selected research reports and publications

Publicly available software (R packages)

  • GPareto: Gaussian Processes for Pareto Front Estimation and Optimization
  • kergp: Gaussian Process models with customised covariance kernels
  • KrigInv: Kriging-based Inversion for Deterministic and Noisy Computer Experiments
  • MuFiCokriging: Multi-Fidelity Cokriging models
  • DiceKriging: Kriging methods for computer experiments (Continuation of a package initiated within the DICE Consortium)
  • DiceOptim : Kriging-based optimization for computer experiments (Continuation of a package initiated within the DICE Consortium)