A Surrogate-Assisted Variable Grouping Algorithm for General Large Scale Global Optimization Problems

TL;DR

This paper introduces SVG, a surrogate-assisted variable grouping algorithm that improves problem decomposition in large-scale global optimization by accurately detecting variable separability with fewer evaluations.

Contribution

SVG is a novel decomposition method that uses surrogate models and a dynamic search process to accurately identify variable groups, overcoming limitations of existing algorithms.

Findings

SVG outperforms six state-of-the-art algorithms in benchmark tests.

SVG demonstrates broad applicability to various problem types.

SVG significantly enhances cooperative coevolution performance.

Abstract

Problem decomposition plays a vital role when applying cooperative coevolution (CC) to large scale global optimization problems. However, most learning-based decomposition algorithms either only apply to additively separable problems or face the issue of false separability detections. Directing against these limitations, this study proposes a novel decomposition algorithm called surrogate-assisted variable grouping (SVG). SVG first designs a general-separability-oriented detection criterion according to whether the optimum of a variable changes with other variables. This criterion is consistent with the separability definition and thus endows SVG with broad applicability and high accuracy. To reduce the fitness evaluation requirement, SVG seeks the optimum of a variable with the help of a surrogate model rather than the original expensive high-dimensional model. Moreover, it converts the variable grouping process into a dynamic-binary-tree search one, which facilitates reutilizing historical separability detection information and thus reducing detection times. To evaluate the performance of SVG, a suite of benchmark functions with up to 2000 dimensions, including additively and non-additively separable ones, were designed. Experimental results on these functions indicate that, compared with six state-of-the-art decomposition algorithms, SVG possesses broader applicability and competitive efficiency. Furthermore, it can significantly enhance the optimization performance of CC.