Quantifying uncertainty on Pareto fronts with Gaussian process conditional simulations

DOI10.1016/j.ejor.2014.07.032zbMath1346.90730OpenAlexW2061871300MaRDI QIDQ319103

Olivier Roustant, David Ginsbourger, Mickaël Binois

Publication date: 6 October 2016

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://boris.unibe.ch/64125/8/Quantifying%20uncertainty%20on%20Pareto%20fronts%20with%20Gaussian%20Process%20conditional%20simulations.pdf

zbMATH Keywords

multi-objective optimizationKrigingattainment functionexpected hypervolume improvementVorob'ev expectation

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Multi-objective and goal programming (90C29) Approximation methods and heuristics in mathematical programming (90C59) Applications of statistics (62Pxx)

Related Items (9)

Evolutionary robust optimization in production planning -- interactions between number of objectives, sample size and choice of robustness measure ⋮ Fast update of conditional simulation ensembles ⋮ On the estimation of Pareto fronts from the point of view of copula theory ⋮ Linear programming-based directed local search for expensive multi-objective optimization problems: application to drinking water production plants ⋮ Quantifying Uncertainties on Excursion Sets Under a Gaussian Random Field Prior ⋮ Simulation and multi-objective optimization to improve the final shape and process efficiency of a laser-based material accumulation process ⋮ Expected improvement for expensive optimization: a review ⋮ Four algorithms to construct a sparse kriging kernel for dimensionality reduction ⋮ Targeting solutions in Bayesian multi-objective optimization: sequential and batch versions

Uses Software

• MOEA/D
• EGO
• DiceKriging
• DiceOptim
• ParEGO

Cites Work

• Unnamed Item
• ParEGO
• Hypervolume-based multiobjective optimization: theoretical foundations and practical implications
• An informational approach to the global optimization of expensive-to-evaluate functions
• Model-based geostatistics.
• Fast update of conditional simulation ensembles
• On degeneracy and invariances of random fields paths with applications in Gaussian process modelling
• Efficient global optimization of expensive black-box functions
• Interpolation of spatial data. Some theory for kriging
• Nonlinear multiobjective optimization
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Cross validation and maximum likelihood estimations of hyper-parameters of Gaussian processes with model misspecification
• Multivariate versus univariate Kriging metamodels for multi-response simulation models
• The Attainment-Function Approach to Stochastic Multiobjective Optimizer Assessment and Comparison
• Theory of Random Sets
• Evolutionary Multi-Criterion Optimization

This page was built for publication: Quantifying uncertainty on Pareto fronts with Gaussian process conditional simulations