RCMAES: A Robust CMA-ES Variant for CEC2026 Competition
Neural and Evolutionary Computing
2026-05-01 v1
Abstract
This paper proposes RCMAES, a novel variant of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for CEC benchmark optimization. RCMAES integrates a dimension-dependent nonlinear population-size reduction strategy with an adaptive restart mechanism within a pure CMA-ES framework. RCMAES is evaluated on three benchmark suites (CEC2017, CEC2020, and CEC2022) and compared with state-of-the-art DE algorithms as well as its closely related counterpart, BIPOP-aCMAES. Experimental results show that RCMAES achieves competitive and robust performance across all benchmarks.
Keywords
Cite
@article{arxiv.2604.27138,
title = {RCMAES: A Robust CMA-ES Variant for CEC2026 Competition},
author = {Khoirul Faiq Muzakka and Sören Möller and Martin Finsterbusch},
journal= {arXiv preprint arXiv:2604.27138},
year = {2026}
}
Comments
6 pages, accepted manuscript for IEEE CEC 2026 competition track