A performance approximation assisted expensive many- objective evolutionary algorithm

Surrogate-assisted multi-objective evolutionary algorithms have been paid much attention to solve expensive multi-objective problems in recent years. However, with the number of objectives increasing, an improper solution may be picked for expensive objective evalua-tion due to the accumulation error of approximated values on objective functions. Furthermore, the time to construct surrogate models for all objectives will significantly increase. Thus, in this paper, Gaussian process (GP) models are proposed for performance indicators instead of for objective functions. Furthermore, solutions are selected from either of two ways to be evaluated using the expensive objective function. When there are non-dominated solutions found so far that are approximated, they will be exactly eval-uated using the objective function. Otherwise, the solution with the maximum approxima-tion uncertainty among the current population will be evaluated using the real objective functions. The efficiency of the presented approach is validated on the DTLZ test suite with 3, 6, 10, 15, and 20 objectives, MaF benchmark problems with 3, 6, 10, 15, and 20 objec-tives, and a real-world optimization problem called filter design. The experimental results show that the method proposed in this paper is competitive compared to recently pro-posed peer algorithms for expensive many-objective problems.(c) 2023 Published by Elsevier Inc.

Automated summary

Surrogate-assisted multi-objective evolutionary algorithms have been focused on to solve expensive multi-objective problems. Gaussian process models are proposed for performance indicators instead of objective functions. The efficiency of the approach is validated on test suites and a real-world optimization problem, and it is found to be competitive compared to peer algorithms for expensive many-objective problems.