Enabling High-Dimensional Surrogate-Assisted Optimization by Using Sliding Windows

A major drawback of surrogate-assisted evolutionary algorithms is their limited ability to perform in high-dimensional scenarios. This paper describes a possible meta-algorithm scheme for the application of surrogate models to high-dimensional optimization problems. The main assumption of the proposed method is that for some of these expensive problems the nonlinear interactions between variables are sparse. If these interactions can be represented as a band matrix, they can be exploited by applying low-dimensional heuristic solvers in a sliding window fashion to the high-dimensional problem. A special type of composite test function is presented and the proposed meta-algorithm is compared against standard evolutionary algorithms.