Publications

Papers are sorted by date and gathered in several categories: random fields models, design of experiments, sensitivity analysis, optimization, software, econometrics. Most of them can be found in GoogleScholar, HAL or ArXiv.

---

Random field models

• Characterization of the second order random fields subject to linear distributional PDE Slides constraints, I. Henderson, P. Noble, O. Roustant (+2023), to appear in Bernoulli. [Preprint]
• High-dimensional additive Gaussian processes under monotonicity constraints, A.F. López-Lopera, F. Bachoc, O. Roustant (2022), NeurIPS 2022. [Preprint]
• Revealing the interlevel dependence structure of categorical inputs in numerical environmental simulations with kernel model selection, J. Rohmer, O. Roustant, S. Lecacheux, J.-C. Manceau (2022), Environmental Modelling and Software, 151, 105380. [Preprint]
• Sequential construction and dimension reduction of Gaussian processes under inequality constraints, F. Bachoc, A. F. Lopez-Lopéra, O. Roustant (2022), SIAM Journal on Mathematics of Data Science, 4 (2), 772-800. [Preprint] [Slides]
• Group kernels for Gaussian process metamodels with categorical inputs, O. Roustant, E. Padonou, Y. Deville, A. Clément, G. Perrin, J. Giorla, H. Wynn (2020), SIAM/ASA Journal on Uncertainty Quantification, 8 (2), 775-806. [Slides]
• On the validity of parametric block correlation matrices with constant within and between group correlations, O. Roustant and Y. Deville (2018).
• Approximating Gaussian Process Emulators with Linear Inequality Constraints and Noisy Observations via MC and MCMC, A. F. López-Lopera, F. Bachoc, N. Durrande, J. Rohmer, D. Idier and O. Roustant (2020), proceedings of MCQMC 2018 conference, 363-381. [Preprint]
• Finite-dimensional Gaussian approximation with linear inequality constraints, A. F. López-Lopera, F. Bachoc, N. Durrande and O. Roustant (2018), SIAM/ASA Journal on Uncertainty Quantification, 6 (3), 1224–1255.
• Universal prediction distribution for surrogate models, M. Ben Salem, O. Roustant, F. Gamboa, L. Tomaso (2017), SIAM/ASA Journal on Uncertainty Quantification, 5 (1), 1086-1109.
• Polar Gaussian processes and experimental designs in circular domains, E. Padonou, O. Roustant (2016), SIAM/ASA Journal on Uncertainty Quantification, 4 (1), 1014-1033. [Slides]
• Computer experiments with functional inputs and scalar outputs by a norm-based approach, T. Muehlenstaedt, J. Fruth, O. Roustant (2017), 27 (4), 1083–1097, Statistics & Computing [Preprint on arXiv].
• On ANOVA decompositions of kernels and Gaussian random field paths, D. Ginsbourger, O. Roustant, D. Schuhmacher, N. Durrande, N. Lenz (2016), in Monte Carlo and Quasi Monte Carlo Methods, Proceedings in Mathematics & Statistics, Springer, 163, 315-330 [Preprint on ArXiv].
• On degeneracy and invariances of random fields paths with applications in Gaussian process modelling, D. Ginsbourger, O. Roustant, N. Durrande (2016), Journal of Statistical Planning and Inference, 170, 117-128. [Preprint on HAL]
• Argumentwise invariant kernels for the approximation of invariant functions, D. Ginsbourger, X. Bay, O. Roustant, L. Carraro (2012), Annales de la Faculté des Sciences de Toulouse, XXI (3), 501-527.
• Additive covariance kernels for high-dimensional Gaussian process modeling, N. Durrande, D. Ginsbourger, O. Roustant (2012), Annales de la Faculté des Sciences de Toulouse, XXI (3), 481-499. [Preprint on HAL]
• Data-driven Kriging models based on FANOVA-decomposition, T. Muehlenstaedt, O. Roustant, L. Carraro, S. Kuhnt (2012), Statistics & Computing, 22 (3), 723-738.[Preprint on HAL][Slides]
• Kriging as an alternative for a more precise analysis of output parameters in nuclear safety – Large break LOCA calculation, O. Roustant, J. Joucla, P. Probst (2010), Applied Stochastic Models in Business and Industry, 26, 565-576.
• A Note on the Choice and the Estimation of Kriging Models for the Analysis of Computer Experiments, D. Ginsbourger, D. Dupuy, A. Badea, L. Carraro and O. Roustant (2009), Applied Stochastic Models in Business and Industry, 25 (2), p. 115-131.

Design of experiments

• Spectral decomposition of H¹(μ) and Poincaré inequality on a compact interval – Application to kernel quadrature, O. Roustant, N. Lüthen, F. Gamboa (+2023). [Preprint][Slides]
• Gaussian Process-Based Dimension Reduction for Goal-Oriented Sequential Design, M. Ben Salem, F. Bachoc, O. Roustant, F. Gamboa, L. Tomaso (2019). SIAM/ASA Journal on Uncertainty Quantification, 7(4), 1369–1397.
• Kernels and designs for modelling invariant functions: From group invariance to additivity, D. Ginsbourger, N. Durrande, O. Roustant (2013), in D. Ucinski, A. C. Atkinson and M. Patan, MODA – 10 – Advances in Model-Oriented Design and Analysis, Springer (Physica-Verlag), p. 107-115. [Preprint on HAL]
• Adaptive designs of experiments for accurate approximation of a target region, V. Picheny, D. Ginsbourger, O. Roustant, R.T. Haftka, N-H. Kim (2010), Journal of Mechanical Design, 132 (7), 071008 (9 pages).
• A radial scanning statistic for selecting space-filling designs in computer experiments, O. Roustant, J. Franco, L. Carraro, A. Jourdan (2010), in A. Giovagnoli, A.C. Atkinson, B. Thorsney and C. May, “MODA – 9 – Advances in Model-Oriented Design and Analysis”, Springer (Physica-Verlag), p. 189-196. [Slides]
• Construction d’un critère d’optimalité pour plans d’expériences numériques dans le cadre de la quantification d’incertitudes, L. Carraro, B. Corre, C. Helbert, O. Roustant (2005), Revue de Statistique Appliquée, LIII (4), p. 87-103.

Sensitivity analysis

• Global sensitivity analysis using derivative-based sparse Poincaré chaos expansions (+2023), N. Lüthen, O. Roustant, F. Gamboa, B. Iooss, S. Marelli, B. Sudret, to appear in the International Journal for Uncertainty Quantification [Preprint]
• Linking the Hoeffding–Sobol and Möbius formulas through a decomposition of Kuo, Sloan, Wasilkowski, and Wozniakowski, C. Mercadier, O. Roustant, C. Genest (2022), Statistics and Probability Letters, 185, 109419. [Preprint]
• Functional principal component analysis for global sensitivity analysis of model with spatial output, T.V.E. Perrin, O. Roustant, J. Rohmer, O. Alata, J.P. Naulin, D. Idier, R. Pedreros, D. Moncoulon, P. Tinard (2021), Reliability Engineering & System Safety, 211, 107522. [Preprint]
• Parseval inequalities and lower bounds for variance-based sensitivity indices, O Roustant, F. Gamboa, B Iooss (2020), Electronic Journal of Statistics, 14(1), p. 386-412. [Slides]
• The Hoeffding-Sobol decomposition in extreme value theory. Exploring the asymptotic dependence structure, C. Mercadier, O. Roustant (2019), Extremes, 22 (2), p. 343-372. [Preprint on HAL]
• Support indices: Measuring the effects of input variables over their support, J. Fruth, O. Roustant, S. Kuhnt (2019), Reliability Engineering & System Safety, 187, p. 17-27 [Preprint on HAL]
• Poincaré inequalities on intervals – application to sensitivity analysis, O. Roustant, F. Barthe, B. Iooss (2017), Electronic Journal of Statistics, 11 (2), p. 3081-3119. [Slides]
• Sequential designs for sensitivity analysis of functional inputs in computer experiments, J. Fruth, O. Roustant, S. Kuhnt (2015), Reliability Engineering & System Safety, 134, p. 260-267. [Preprint on HAL]
• Crossed-derivative based sensitivity measures for interaction screening, O. Roustant, J. Fruth, B. Iooss, S. Kuhnt (2014), Mathematics and Computers in Simulation, 105, p. 105-118. [Preprint on HAL]
• Total interaction index: A variance-based sensitivity index for second-order interaction screening, J. Fruth, O. Roustant, S. Kuhnt (2014), Journal of Statistical Planning and Inference, 147, p. 212-223. [Preprint on HAL]
• ANOVA kernels and RKHS of zero mean functions for model-based sensitivity analysis, N. Durrande, D. Ginsbourger, O. Roustant, L. Carraro (2013), Journal of Multivariate Analysis, 115 (57-67). [Preprint on HAL][R code]
• Calculations of Sobol indices for the Gaussian process metamodel, A. Marrel, B. Iooss, B. Laurent and O. Roustant (2009)”, Reliability Engineering & System Safety, 94 (3), p. 742-751. [Preprint on HAL]

Optimization

• A comparison of mixed-variables Bayesian optimization approaches, J. Cuesta-Ramirez, R. Le Riche, O. Roustant, G. Perrin, C. Durantin and A. Glière (2022). Advanced Modeling and Simulation in Engineering Sciences, 9:6. [Preprint]
• Mixed global optimization by algorithms composition: an empirical study with a focus on Bayesian approaches, M.-L. Cauwet, R. Le Riche, O. Roustant. Communication at EURO 2019 conference.
• On the choice of the low-dimensional domain for global optimization via random embeddings, M. Binois, D. Ginsbourger, O. Roustant (2020), Journal of Global Optimization, 76(1), p. 69-90. [Preprint]
• On the estimation of Pareto fronts from the point of view of copula theory, M. Binois, D. Rullière, O. Roustant (2015), Information Sciences, 324, p. 270-285. [Preprint on HAL]
• A warped kernel improving robustness in Bayesian optimization via random embeddings, M. Binois, D. Ginsbourger, O. Roustant (2015), LION 9, 281-286, Springer. [Preprint on HAL]
• Quantifying uncertainty on Pareto fronts with Gaussian Process conditional simulations, M. Binois, D. Ginsbourger, O. Roustant (2015), European Journal of Operational Research, 243 (2, 1), p. 386–394. [Preprint on HAL]
• L’incertitude en conception : formalisation, estimation, G. Pujol, R. Le Riche, O. Roustant, X. Bay (2009), in Optimisation multidisciplinaire en mécanique, Hermès. [Supplementary material – R code twobars.zip]

Software

• DiceKriging, DiceOptim: two R packages for the analysis of computer experiments by kriging-based metamodelling and optimization, O. Roustant, D. Ginsbourger, Y. Deville (2012), Journal of Statistical Software, 51(1), 1-55. [Updated version on HAL]

Econometrics

• Composition chimique des dépôts atmosphériques à l’horizon 2020-2040, A. Pascaud, S. Sauvage, C. Pagé O. Roustant, A. Probst, M. Nicolas, L. Croisé, A. Mezdour, P. Coddeville (2016), La météorologie, 92, p. 56-65.
• Robust monitoring of an industrial IT system in the presence of structural change, E. Padonou, O. Roustant, M. Lutz (2015), Quality and Reliability Engineering International, 31 (6), p. 949–962. [Preprint on HAL]
• Methods and applications for IT capacity decisions: Bringing management frameworks into practice, M. Lutz, X. Boucher, O. Roustant (2013), Journal of Decision Systems, 22 (4), p. 332-355.
• Information Technologies capacity planning in manufacturing systems: Proposition for a modelling process and application in the semiconductor industry, M. Lutz, X. Boucher, O. Roustant (2012), Computers in Industry, 63 (7), p. 659-668.
• Couplage entre système de production industriel et technologies de l’information : modélisation et création de connaissance, M. Lutz, X. Boucher, O. Roustant , M.-A. Girard, (2012), Ingénierie des Systèmes d’Information, 17 (4), p. 95-117.
• Un modèle de régression pour données censurées de retombées atmosphériques, A. Pascaud, O. Roustant, S. Sauvage, P. Coddeville (2011), Actes du colloque Les STIC pour l’Environnement, Ed. Mines ParisTech, p. 71-84.
• A bootstrap approach to the pricing of weather derivatives, O. Roustant, J-P. Laurent, X. Bay, L. Carraro (2005), Bulletin Français d’Actuariat, p. 163-171
• Estimation risk in the pricing of weather derivatives, O. Roustant, J-P. Laurent, X. Bay, L. Carraro (2004), Banque & Marchés, 72, p. 5 -16
• Modélisation des températures, M. Moréno, O. Roustant (2003), in: La réassurance : approche technique, Blondeau J. et Partrat C., Economica, p. 600-615.
• Une application de deux modèles économétriques de température à la gestion des risques climatiques (1ère partie), O. Roustant (2002), Banque & Marchés, 58, p. 22-29
• Une application de deux modèles économétriques de température à la gestion des risques climatiques (2ème partie), O. Roustant (2002), Banque & Marchés, 59, p. 36-44.