Abstract
The choice of parameter values in evolutionary algorithms greatly affects their performance. Many popular parameter tuning techniques are limited by the tuning budget for finding a good set of parameter values. Recently, we proposed an approach to parameter tuning that uses fitness landscape analysis and machine learning to recommend good parameter values for problem instances based on their landscape features. Using fitness landscape features allows to identify similar problems and use parameter tuning data obtained on benchmark problems, significantly reducing the tuning budget requirements.
In this paper, we present our study of the landscape-aware parameter tuning approach for the \({(1 + (\lambda , \lambda ))}\) genetic algorithm. We evaluate the performance of the algorithm tuned by this approach on the linear integer weights problem and the MAX-3SAT problem, in addition to the W-model problem used for the collection of training data. Our results suggest that the proposed approach allows to make meaningful parameter choices and shows good performance without high fitness evaluation budget requirements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bassin, A., Buzdalov, M.: The \((1+(\lambda ,\lambda ))\) genetic algorithm for permutations. In: Proceedings of Genetic and Evolutionary Computation Conference Companion, pp. 1669–1677. ACM (2020)
Dang, N., Doerr, C.: Hyper-parameter tuning for the \((1+(\lambda ,\lambda ))\) GA. In: Proceedings of Genetic and Evolutionary Computation Conference, pp. 889–897 (2019)
Doerr, B., Doerr, C.: Optimal parameter choices through self-adjustment: applying the 1/5-th rule in discrete settings. In: Proceedings of Genetic and Evolutionary Computation Conference, pp. 1335–1342 (2015)
Doerr, B., Doerr, C., Ebel, F.: From black-box complexity to designing new genetic algorithms. Theor. Comput. Sci. 567, 87–104 (2015)
Doerr, C., Wang, H., Ye, F., van Rijn, S., Bäck, T.: IOHprofiler: a benchmarking and profiling tool for iterative optimization heuristics (2018). https://arxiv.org/abs/1810.05281, IOHprofiler is available at https://github.com/IOHprofiler
Eiben, A.E., Smit, S.K.: Parameter tuning for configuring and analyzing evolutionary algorithms. Swarm Evol. Comput. 1(1), 19–31 (2011)
Eiben, Á.E., Michalewicz, Z., Schoenauer, M., Smith, J.E.: Parameter control in evolutionary algorithms. In: Lobo, F.G., Lima, C.F., Michalewicz, Z. (eds.) Parameter Setting in Evolutionary Algorithms. SCI, vol. 54, pp. 19–46. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-69432-8_2
Garey, M.R., Johnson, D.S.: Computers and Intractability: A Guide to the Theory of NP-Completeness. W. H. Freeman & Co., New York (1979)
Hutter, F., Hoos, H.H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration. In: Coello, C.A.C. (ed.) LION 2011. LNCS, vol. 6683, pp. 507–523. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25566-3_40
Janković, A., Doerr, C.: Adaptive landscape analysis. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 2032–2035 (2019)
Karafotias, G., Hoogendoorn, M., Eiben, Á.E.: Parameter control in evolutionary algorithms: trends and challenges. IEEE Trans. Evol. Comput. 19(2), 167–187 (2015)
Kerschke, P., Trautmann, H.: Automated algorithm selection on continuous black-box problems by combining exploratory landscape analysis and machine learning. Evol. Comput. 27(1), 99–127 (2019)
Lobo, F.G., Lima, C.F., Michalewicz, Z. (eds.): Parameter Setting in Evolutionary Algorithms. SCI, vol. 54. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-69432-8
López-Ibáñez, M., Dubois-Lacoste, J., Cáceres, L.P., Stützle, T., Birattari, M.: The irace package: iterated racing for automatic algorithm configuration. Oper. Res. Perspect. 3, 43–58 (2016)
Mersmann, O., Bischl, B., Trautmann, H., Preuss, M., Weihs, C., Rudolph, G.: Exploratory landscape analysis. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, pp. 829–836 (2011)
Mersmann, O., Preuss, M., Trautmann, H.: Benchmarking evolutionary algorithms: towards exploratory landscape analysis. In: Schaefer, R., Cotta, C., Kołodziej, J., Rudolph, G. (eds.) PPSN 2010. LNCS, vol. 6238, pp. 73–82. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15844-5_8
Ochoa, G., Malan, K.: Recent advances in fitness landscape analysis. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion. GECCO 2019, pp. 1077–1094. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3319619.3323383
Pikalov, M., Mironovich, V.: Automated parameter choice with exploratory landscape analysis and machine learning. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion. GECCO 2021, pp. 1982–1985 (2021). https://doi.org/10.1145/3449726.3463213
Weise, T., Wu, Z.: Difficult features of combinatorial optimization problems and the tunable W-Model benchmark problem for simulating them. In: Proceedings of Genetic and Evolutionary Computation Conference Companion, pp. 1769–1776 (2018)
Acknowledgments
The reported study was funded by RFBR and CNRS, project number 20-51-15009.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Pikalov, M., Mironovich, V. (2022). Parameter Tuning for the \({(1 + (\lambda , \lambda ))}\) Genetic Algorithm Using Landscape Analysis and Machine Learning. In: Jiménez Laredo, J.L., Hidalgo, J.I., Babaagba, K.O. (eds) Applications of Evolutionary Computation. EvoApplications 2022. Lecture Notes in Computer Science, vol 13224. Springer, Cham. https://doi.org/10.1007/978-3-031-02462-7_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-02462-7_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02461-0
Online ISBN: 978-3-031-02462-7
eBook Packages: Computer ScienceComputer Science (R0)