DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization
We present two recently released R packages, DiceKriging and DiceOptim, for the approximation and the optimization of expensive-to-evaluate deterministic functions. Following a self-contained mini tutorial on Kriging-based approximation and optimization, the functionalities of both packages are deta...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Foundation for Open Access Statistics
2012-10-01
|
| Series: | Journal of Statistical Software |
| Subjects: | |
| Online Access: | http://www.jstatsoft.org/v51/i01/paper |
| _version_ | 1818603743258607616 |
|---|---|
| author | Olivier Roustant David Ginsbourger Yves Deville |
| author_facet | Olivier Roustant David Ginsbourger Yves Deville |
| author_sort | Olivier Roustant |
| collection | DOAJ |
| description | We present two recently released R packages, DiceKriging and DiceOptim, for the approximation and the optimization of expensive-to-evaluate deterministic functions. Following a self-contained mini tutorial on Kriging-based approximation and optimization, the functionalities of both packages are detailed and demonstrated in two distinct sections. In particular, the versatility of DiceKriging with respect to trend and noise specifications, covariance parameter estimation, as well as conditional and unconditional simulations are illustrated on the basis of several reproducible numerical experiments. We then put to the fore the implementation of sequential and parallel optimization strategies relying on the expected improvement criterion on the occasion of DiceOptim’s presentation. An appendix is dedicated to complementary mathematical and computational details. |
| first_indexed | 2024-12-16T13:28:01Z |
| format | Article |
| id | doaj.art-2b4e0a22f9dd40cfab4ce4453bbbc6fa |
| institution | Directory Open Access Journal |
| issn | 1548-7660 |
| language | English |
| last_indexed | 2024-12-16T13:28:01Z |
| publishDate | 2012-10-01 |
| publisher | Foundation for Open Access Statistics |
| record_format | Article |
| series | Journal of Statistical Software |
| spelling | doaj.art-2b4e0a22f9dd40cfab4ce4453bbbc6fa2022-12-21T22:30:08ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602012-10-01511DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and OptimizationOlivier RoustantDavid GinsbourgerYves DevilleWe present two recently released R packages, DiceKriging and DiceOptim, for the approximation and the optimization of expensive-to-evaluate deterministic functions. Following a self-contained mini tutorial on Kriging-based approximation and optimization, the functionalities of both packages are detailed and demonstrated in two distinct sections. In particular, the versatility of DiceKriging with respect to trend and noise specifications, covariance parameter estimation, as well as conditional and unconditional simulations are illustrated on the basis of several reproducible numerical experiments. We then put to the fore the implementation of sequential and parallel optimization strategies relying on the expected improvement criterion on the occasion of DiceOptim’s presentation. An appendix is dedicated to complementary mathematical and computational details.http://www.jstatsoft.org/v51/i01/papercomputer experimentsGaussian processesglobal optimization |
| spellingShingle | Olivier Roustant David Ginsbourger Yves Deville DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization Journal of Statistical Software computer experiments Gaussian processes global optimization |
| title | DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization |
| title_full | DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization |
| title_fullStr | DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization |
| title_full_unstemmed | DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization |
| title_short | DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization |
| title_sort | dicekriging diceoptim two r packages for the analysis of computer experiments by kriging based metamodeling and optimization |
| topic | computer experiments Gaussian processes global optimization |
| url | http://www.jstatsoft.org/v51/i01/paper |
| work_keys_str_mv | AT olivierroustant dicekrigingdiceoptimtworpackagesfortheanalysisofcomputerexperimentsbykrigingbasedmetamodelingandoptimization AT davidginsbourger dicekrigingdiceoptimtworpackagesfortheanalysisofcomputerexperimentsbykrigingbasedmetamodelingandoptimization AT yvesdeville dicekrigingdiceoptimtworpackagesfortheanalysisofcomputerexperimentsbykrigingbasedmetamodelingandoptimization |