An investigation of F-Race training strategies for cross domain optimisation with memetic algorithms

Gümüş, Düriye Betül; Özcan, Ender; Atkin, Jason; Drake, John H.

Abstract

Parameter tuning is a challenging and time-consuming task, crucial to obtaining improved metaheuristic performance. There is growing interest in cross-domain search methods, which consider a range of optimisation problems rather than being specialised for a single domain. Metaheuristics and hyper-heuristics are typically used as high-level cross-domain search methods, utilising problem-specific low-level heuristics for each problem domain to modify a solution. Such methods have a number of parameters to control their behaviour, whose initial settings can influence their search behaviour significantly. Previous methods in the literature either fix these parameters based on previous experience, or set them specifically for particular problem instances. There is a lack of extensive research investigating the tuning of these parameters systematically. In this paper, F-Race is deployed as an automated cross-domain parameter tuning approach. The parameters of a steady-state memetic algorithm and the low-level heuristics used by this algorithm are tuned across nine single-objective problem domains, using different training strategies and budgets to investigate whether F-Race is capable of effectively tuning parameters for cross-domain search. The empirical results show that the proposed methods manage to find good parameter settings, outperforming many methods from the literature, with different configurations identified as the best depending upon the training approach used.

Citation

Gümüş, D. B., Özcan, E., Atkin, J., & Drake, J. H. (2023). An investigation of F-Race training strategies for cross domain optimisation with memetic algorithms. Information Sciences, 619, 153-171. https://doi.org/10.1016/j.ins.2022.11.008

• Journal Article Type: Article
• Acceptance Date: Nov 4, 2022
• Online Publication Date: Nov 10, 2022
• Publication Date: Jan 1, 2023
• Deposit Date: Nov 17, 2022
• Publicly Available Date: Nov 17, 2022
• Journal: Information Sciences
• Print ISSN: 0020-0255
• Electronic ISSN: 1872-6291
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 619
• Pages: 153-171
• DOI: https://doi.org/10.1016/j.ins.2022.11.008
• Keywords: Artificial Intelligence; Information Systems and Management; Computer Science Applications; Theoretical Computer Science; Control and Systems Engineering; Software
• Public URL: https://nottingham-repository.worktribe.com/output/13749700
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S0020025522012804?via%3Dihub
• Additional Information: Article Title: An investigation of F-Race training strategies for cross domain optimisation with memetic algorithms; Journal Title: Information Sciences; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.ins.2022.11.008