MATSuMoTo: The MATLAB Surrogate Model Toolbox For Computationally Expensive Black-Box Global Optimization Problems

摘要

MATSuMoTo is the MATLAB Surrogate Model Toolbox for computationallyexpensive, black-box, global optimization problems that may have continuous,mixed-integer, or pure integer variables. Due to the black-box nature of theobjective function, derivatives are not available. Hence, surrogate models areused as computationally cheap approximations of the expensive objectivefunction in order to guide the search for improved solutions. Due to thecomputational expense of doing a single function evaluation, the goal is tofind optimal solutions within very few expensive evaluations. The multimodalityof the expensive black-box function requires an algorithm that is able tosearch locally as well as globally. MATSuMoTo is able to address thesechallenges. MATSuMoTo offers various choices for surrogate models and surrogatemodel mixtures, initial experimental design strategies, and samplingstrategies. MATSuMoTo is able to do several function evaluations in parallel byexploiting MATLAB's Parallel Computing Toolbox.