Loading...
Please wait, while we are loading the content...
Similar Documents
MATSuMoTo: The MATLAB Surrogate Model Toolbox For Computationally Expensive Black-Box Global Optimization Problems
| Content Provider | Semantic Scholar |
|---|---|
| Author | Müller, Juliane |
| Copyright Year | 2015 |
| Abstract | AbstractMATSuMoTo is the MATLAB Surrogate Model Toolbox for computationally ex-pensive, black-box, global optimization problems that may have continuous, mixed-integer, or pure integer variables. Due to the black-box nature of the objectivefunction, derivatives are not available. Hence, surrogate models are used as com-putationally cheap approximations of the expensive objective function in order toguide the search for improved solutions. Due to the computational expense of doinga single function evaluation, the goal is to nd optimal solutions within very fewexpensive evaluations. The multimodality of the expensive black-box function re-quires an algorithm that is able to search locally as well as globally. MATSuMoTois able to address these challenges. MATSuMoTo o ers various choices for surro-gate models and surrogate model mixtures, initial experimental design strategies,and sampling strategies. MATSuMoTo is able to do several function evaluations inparallel by exploiting MATLAB’s Parallel Computing Toolbox. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://arxiv.org/pdf/1404.4261v1.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
