No Cover Image

Conference Paper/Proceeding/Abstract 313 views 16 downloads

Using structural bias to analyse the behaviour of modular CMA-ES

Diederick Vermetten, Fabio Caraffini Orcid Logo, Bas van Stein, Anna V. Kononova

Proceedings of the Genetic and Evolutionary Computation Conference Companion

Swansea University Author: Fabio Caraffini Orcid Logo

  • 62444_VoR.pdf

    PDF | Version of Record

    © 2022 Copyright held by the owner/author(s). Released under the terms of a CC-BY License

    Download (2.36MB)

DOI (Published version): 10.1145/3520304.3534035

Abstract

The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a commonly used iterative optimisation heuristic for optimising black-box functions. CMA-ES comes in many flavours with different configuration settings. In this work, we investigate whether CMA-ES suffers from structural bias and which...

Full description

Published in: Proceedings of the Genetic and Evolutionary Computation Conference Companion
ISBN: 978-1-4503-9268-6
Published: New York, NY, USA ACM 2022
URI: https://cronfa.swan.ac.uk/Record/cronfa62444
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a commonly used iterative optimisation heuristic for optimising black-box functions. CMA-ES comes in many flavours with different configuration settings. In this work, we investigate whether CMA-ES suffers from structural bias and which modules and parameters affect the strength and type of structural bias. Structural bias occurs when an algorithm or a component of the algorithm biases the search towards a specific direction in the search space irrespective of the objective function. In addition to this investigation, we propose a method to assess the relationship between structural bias and the performance of configurations with different types of bias on the BBOB suite of benchmark functions. Surprisingly for such a popular algorithm, 90.3% of the 1 620 CMA-ES configurations were found to have Structural Bias. Some interesting patterns between module settings and bias types are presented and further insights are discussed.
College: Faculty of Science and Engineering