Optimizing CMA-ES with CMA-ES

André Thomaser, André Thomaser, Marc-Eric Vogt, Thomas Bäck, Anna Kononova

2023

Abstract

The performance of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is significantly affected by the selection of the specific CMA-ES variant and the parameter values used. Furthermore, optimal CMA-ES parameter configurations vary across different problem landscapes, making the task of tuning CMA-ES to a specific optimization problem a challenging mixed-integer optimization problem. In recent years, several advanced algorithms have been developed to address this problem, including the Sequential Model-based Algorithm Configuration (SMAC) and the Tree-structured Parzen Estimator (TPE). In this study, we propose a novel approach for tuning CMA-ES by leveraging CMA-ES itself. Therefore, we combine the modular CMA-ES implementation with the margin extension to handle mixed-integer optimization problems. We show that CMA-ES can not only compete with SMAC and TPE but also outperform them in terms of wall clock time.

Paper Citation

in Harvard Style

Thomaser A., Vogt M., Bäck T. and Kononova A. (2023). Optimizing CMA-ES with CMA-ES. In Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA; ISBN 978-989-758-674-3, SciTePress, pages 214-221. DOI: 10.5220/0012179400003595

in Bibtex Style

@conference{ecta23,
author={André Thomaser and Marc-Eric Vogt and Thomas Bäck and Anna Kononova},
title={Optimizing CMA-ES with CMA-ES},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA},
year={2023},
pages={214-221},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012179400003595},
isbn={978-989-758-674-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA
TI - Optimizing CMA-ES with CMA-ES
SN - 978-989-758-674-3
AU - Thomaser A.
AU - Vogt M.
AU - Bäck T.
AU - Kononova A.
PY - 2023
SP - 214
EP - 221
DO - 10.5220/0012179400003595
PB - SciTePress