This paper studies simulation-based optimization with multiple outputs. It assumes that the simulation model has one random objective function and must satisfy given constraints on the other random outputs. It presents a statistical procedure for test- ing whether a specific input combination (proposed by some optimization heuristic) satisfies the Karush-Kuhn-Tucker (KKT) first-order optimality conditions. The pa- per focuses on "expensive" simulations, which have small sample sizes. The paper applies the classic t test to check whether the specific input combination is feasi- ble, and whether any constraints are binding; it applies bootstrapping (resampling) to test the estimated gradients in the KKT conditions. The new methodology is applied to three examples, which gives encouraging empirical results.
|Place of Publication||Tilburg|
|Number of pages||31|
|Publication status||Published - 2007|
|Name||CentER Discussion Paper|
- Stopping rule
- response surface methodology
- design of experiments
Bettonvil, B. W. M., Del Castillo, E., & Kleijnen, J. P. C. (2007). Statistical Testing of Optimality Conditions in Multiresponse Simulation-based Optimization (Revision of 2005-81). (CentER Discussion Paper; Vol. 2007-45). Operations research.