Improving Optimization With Gaussian Processes in the Covariance Matrix Adaptation Evolution Strategy

Authors: J. Tumpach, J. Koza, Martin Holeňa
Publication year: 2023
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Proceedings of the 23st Conference Information Technologies – Applications and Theory (ITAT 2023)
Bibliographic citation: TUMPACH, J., KOZA, J., HOLEŇA, Martin. Improving Optimization With Gaussian Processes in the Covariance Matrix Adaptation Evolution Strategy. In: BREJOVÁ, B., CIENCIALOVÁ, L., HOLEŇA, M., JAJCAY, R., JAJCAYOVÁ, T., LEXA, M., MRÁZ, F., PARDUBSKÁ, D., PLÁTEK, M., eds. Proceedings of the 23st Conference Information Technologies – Applications and Theory (ITAT 2023). Aachen: Technical University & CreateSpace Independent Publishing, 2023, S. 82-88. CEUR Workshop Proceedings, 3498. ISSN 1613-0073. Dostupné z: https://ceur-ws.org/Vol-3498/paper10.pdf
ID: 579713
Online record: View online record

Abstract

This paper explores the use of Gaussian processes (GPs) in the covariance matrix adaptation evolution strategy (CMA-ES) for black-box optimization. GPs are powerful probabilistic models that capture complex relationships, making them suitable for modeling uncertain objective functions. Integrating GPs into the CMA-ES improves exploration and adaptation in the search space, enhancing convergence speed and solution quality. The paper describes a novel implementation framework allowing to use GPs as surrogate models for the CMA-ES. That framework findings encourage further research to advance the application of GPs in black-box optimization.