Publication detail
An Investigation of Inherent Structural Bias in Established Benchmark Sets
IBEHEJ, D. TZANETOS, A. JUŘÍČEK, M. KŮDELA, J.
English title
An Investigation of Inherent Structural Bias in Established Benchmark Sets
Type
Paper in proceedings (conference paper)
Language
en
Original abstract
In this paper, we investigate the inherent structural bias of BBOB and CEC benchmark sets. First, we theoretically derive the advantage of central evaluation against random search on the Sum of Squares-like functions. We then provide an experimental analysis of the effectiveness of the central evaluation on functions from BBOB, CEC2014, and CEC2017. We utilize four variants of the Differential Evolution (DE) algorithm, in which by changing the boundary handling technique, we introduce different types of structural bias in the method and show the link between the performance of the biased DE variants and the inherent biases in the benchmark sets. We find that the high use of Sum of Squares-like functions and the BBOB-specific location of the optima give a substantial advantage to the center-biased DE variants, especially in high dimension on low function evaluation settings. On the selected CEC functions, this effect was much less pronounced.
Keywords in English
Benchmarking; Bound Handling Techniques; Differential Evolution; Structural Bias
Released
2025-08-11
Publisher
Association for Computing Machinery, Inc
ISBN
9798400714641
Book
Gecco 2025 Companion Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion
Pages from–to
123–126
Pages count
4
BIBTEX
@inproceedings{BUT200143,
author="David {Ibehej} and {} and Martin {Juříček} and Jakub {Kůdela}",
title="An Investigation of Inherent Structural Bias in Established Benchmark Sets",
booktitle="Gecco 2025 Companion Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion",
year="2025",
pages="123--126",
publisher="Association for Computing Machinery, Inc",
doi="10.1145/3712255.3726665",
isbn="9798400714641"
}