Abstract
While solving expensive multi-objective optimization problems, there may be stringent limits on the number of allowed function evaluations. Surrogate models are commonly used for such problems where calls to surrogates are made in lieu of calls to the true objective functions. The surrogates can also be used to identify infill points for evaluation, i.e., solutions that maximize certain performance criteria. One such infill criteria is the maximization of predicted hypervolume, which is the focus of this study. In particular, we are interested in investigating if better estimate of the normalization bounds could help in improving the performance of the surrogate assisted optimization algorithm. Towards this end, we propose a strategy to identify a better ideal point than the one that exists in the current archive. Numerical experiments are conducted on a range of problems to test the efficacy of the proposed method. The approach outperforms conventional forms of normalization in some cases, while providing comparable results for others. We provide critical insights on the search behavior and relate them with the underlying properties of the test problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Asafuddoula, M., Singh, H.K., Ray, T.: An enhanced decomposition-based evolutionary algorithm with adaptive reference vectors. IEEE Trans. Cybern. 48(8), 2321–2334 (2017)
Bader, J., Zitzler, E.: HypE: an algorithm for fast hypervolume-based many-objective optimization. Evol. Comput. 19(1), 4 (2011)
Beume, N., Naujoks, B., Emmerich, M.: SMS-EMOA: multiobjective selection based on dominated hypervolume. Eur. J. Oper. Res. 181, 1653–1669 (2007)
Bhattacharjee, K.S., Singh, H.K., Ray, T.: Multiple surrogate-assisted many-objective optimization for computationally expensive engineering design. J. Mech. Des. 140(5), 1–10 (2018)
Blank, J., Deb, K., Roy, P.C.: Investigating the normalization procedure of NSGA-III. In: Deb, K., et al. (eds.) EMO 2019. LNCS, vol. 11411, pp. 229–240. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12598-1_19
Habib, A., Singh, H.K., Chugh, T., Ray, T., Miettinen, K.: A multiple surrogate assisted decomposition-based evolutionary algorithm for expensive multi/many-objective optimization. IEEE Trans. Evol. Comput. 23(6), 1000–1014 (2019)
He, L., Ishibuchi, H., Trivedi, A., Srinivasan, D.: Dynamic normalization in MOEA/D for multiobjective optimization. In: IEEE Congres on Evolutionary Computation (CEC) (2020)
Huband, S., Hingston, P., Barone, L., While, L.: A review of multiobjective test problems and a scalable test problem toolkit. IEEE Trans. Evol. Comput. 10(5), 477–506 (2006)
Ishibuchi, H., Imada, R., Setoguchi, Y., Nojma, Y.: How to specify a reference point in hypervolume calculation for fair performance comparison. Evol. Comput. 26(3), 411–440 (2018)
Jones, D.R., Schonlau, M., Welch, W.J.: Efficient global optimization of expensive black-box functions. J. Global Optim. 13, 455–492 (1998). https://doi.org/10.1023/A:1008306431147
Deb, K., Thiele, L., Laumanns, M., Zitzler, E.: Scalable test problems for evolutionary multiobjective optimization. In: Abraham, A., Jain, L., Goldberg, R. (eds.) Evolutionary Multiobjective Optimization. AI&KP, pp. 105–145. Springer, London (2005). https://doi.org/10.1007/1-84628-137-7_6
Knowles, J.: ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems. IEEE Trans. Evol. Comput. 10(1), 50–66 (2006)
Liu, Y., Ishibuchi, H., Yen, G.G., Nojima, Y., Masuyama, N., Han, Y.: On the normalization in evolutionary multi-modal multi-objective optimization. In: IEEE Congres on Evolutionary Computation (CEC) (2020)
Lophaven, S.N., Nielsen, H.B., Sondergaard, J.: A Matlab kriging toolbox. Technical report, Technical University of Denmark (2002)
Miettinen, K.: Nonlinear Multiobjective Optimization, vol. 12. Springer, Heidelberg (2012)
Singh, H.K.: Understanding hypervolume behavior theoretically for benchmarking in evolutionary multi/many-objective optimization. IEEE Trans. Evol. Comput. 24(3), 603–610 (2020)
Singh, H.K., Isaacs, A., Ray, T.: A Pareto corner search evolutionary algorithm and dimensionality reduction in many-objective optimization problems. IEEE Trans. Evol. Comput. 15(4), 539–556 (2011)
Singh, H.K., Yao, X.: Improvement of reference points for decomposition based multi-objective evolutionary algorithms. In: Shi, Y., et al. (eds.) SEAL 2017. LNCS, vol. 10593, pp. 284–296. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68759-9_24
Storn, R., Price, K.: Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J. Glob. Optim. 11(4), 341–359 (1997). https://doi.org/10.1023/A:1008202821328
Wang, G.G., Shan, S.: Review of metamodeling techniques in support of engineering design optimization. J. Mech. Des. 129(4), 370–380 (2007)
Zapotecas-MartÃnez, S., López-Jaimes, A., GarcÃa-Nájera, A.: LIBEA: a Lebesgue indicator-based evolutionary algorithm for multi-objective optimization. Swarm Evol. Comput. 44, 404–419 (2019)
Zhan, D., Cheng, Y., Liu, J.: Expected improvement matrix-based infill criteria for expensive multiobjective optimization. IEEE Trans. Evol. Comput. 21(6), 956–975 (2017)
Zitzler, E., Deb, K., Thiele, L.: Comparison of multiobjective evolutionary algorithms: empirical results. IEEE Trans. Evol. Comput. 8(2), 173–195 (2000)
Zitzler, E., Thiele, L.: Multiobjective optimization using evolutionary algorithms—a comparative case study. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, H.-P. (eds.) PPSN 1998. LNCS, vol. 1498, pp. 292–301. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0056872
Acknowledgements
The authors would like to acknowledge Discovery Project DP190102591 from the Australian Research Council.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, B., Singh, H.K., Ray, T. (2021). Investigating Normalization Bounds for Hypervolume-Based Infill Criterion for Expensive Multiobjective Optimization. In: Ishibuchi, H., et al. Evolutionary Multi-Criterion Optimization. EMO 2021. Lecture Notes in Computer Science(), vol 12654. Springer, Cham. https://doi.org/10.1007/978-3-030-72062-9_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-72062-9_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72061-2
Online ISBN: 978-3-030-72062-9
eBook Packages: Computer ScienceComputer Science (R0)