Error Analysis of Surrogate Models Constructed Through Operations on Submodels

Model-based methods are popular in derivative-free optimization (DFO). In most of them, a single model function is built to approximate the objective function. This generally based on assumption that one blackbox. However, some real-life and theoretical problems show may consist several blackboxes. those problems, information provided by each blackbox not be equal. this situation, could build multiple sub-models then combined become final model. paper, we analyze relation between accuracy constructed through their operations. We develop broad framework can used as tool error analysis future research DFO algorithms design.