A Stepwise uncertainty reduction approach to constrained global optimization

• Main Author: Picheny, Victor
• Other Authors: Unité de Mathématiques et Informatique Appliquées de Toulouse (MIAT INRA), Institut National de la Recherche Agronomique (INRA)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2014
• Subjects: [MATH]Mathematics [math]; [INFO]Computer Science [cs]; Iceland
• Online Access: https://hal.inrae.fr/hal-02743553; https://hal.inrae.fr/hal-02743553/document; https://hal.inrae.fr/hal-02743553/file/a%20stepwise%20uncertainty%20reduction%20approach%20to%20constrained%20global%20optimization_VP_1.pdf

International audience Using statistical emulators to guide sequential evaluations of complex computer experiments is now a well-established practice. When a model provides multiple outputs, a typical objective is to optimize one of the outputs with constraints (for instance, a threshold not to exceed) on the values of the other outputs. We propose here a new optimization strategy based on the stepwise uncertainty reduction paradigm, which o ers an e cient trade-off between exploration and local search near the boundaries. The strategy is illustrated on numerical examples.