2021/07/26 by Bastien Talgorn, Talgorn, Bastien, Stéphane Alarie +3
Computer Science · Decision Sciences · Engineering · Mathematics · #Advanced Multi-Objective Optimization Algorithms #Advanced Optimization Algorithms Research #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Multi-Criteria Decision Making #Optimization and Control (math.OC) #Optimization and Packing Problems
paper · pdf · doi:10.48550/arxiv.2107.12421
openalex publication_date 2021/07/26 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
We consider computationally expensive blackbox optimization problems and\npresent a method that employs surrogate models and concurrent computing at the\nsearch step of the mesh adaptive direct search (MADS) algorithm. Specifically,\nwe solve a surrogate optimization problem using locally weighted scatterplot\nsmoothing (LOWESS) models to find promising candidate points to be evaluated by\nthe blackboxes. We consider several methods for selecting promising points from\na large number of points. We conduct numerical experiments to assess the\nperformance of the modified MADS algorithm with respect to available CPU\nresources by means of five engineering design problems.\n