A Bayesian approach to constrained single- and multi-objective optimization

• Published in: Journal of global optimization Vol. 67; no. 1-2; pp. 97 - 133
• Main Authors: Feliot, Paul, Bect, Julien, Vazquez, Emmanuel
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2017; Springer; Springer Nature B.V; Springer Verlag
• Subjects: Algorithms; Analysis; Approximation; Bayesian analysis; Computation; Computer Science; Computer simulation; Constraints; Criteria; Design optimization; Machine Learning; Mathematical functions; Mathematics; Mathematics and Statistics; Monte Carlo simulation; Multiple objective analysis; Operations Research; Operations Research/Decision Theory; Optimization; Performance evaluation; Real Functions; Sampling; Simulation; Simulation methods; Statistics; Studies; Subset simulation; Gaussian process; Expected improvement; Sequential Monte Carlo; Multi-objective; Bayesian optimization; Kriging; sequential Monte Carlo; subset simulation; kriging; Gaussian processes; multi-objective optimization; expected improvement

This article addresses the problem of derivative-free (single- or multi-objective) optimization subject to multiple inequality constraints. Both the objective and constraint functions are assumed to be smooth, non-linear and expensive to evaluate. As a consequence, the number of evaluations that can...