A Partition Based Bayesian Multi-objective Optimization Algorithm
- 50 Downloads
The research is aimed at coping with the inherent computational intensity of Bayesian multi-objective optimization algorithms. We propose the implementation which is based on the rectangular partition of the feasible region and circumvents much of computational burden typical for the traditional implementations of Bayesian algorithms. The included results of the solution of testing and practical problems illustrate the performance of the proposed algorithm.
KeywordsNon-convex optimization Multi-objective optimization Bayesian approach
This work was supported by the Research Council of Lithuania under Grant No. P-MIP-17-61. We thank the reviewers for their valuable remarks.
- 7.Feliot P., Bect J., Vazquez E.: User preferences in Bayesian multi-objective optimization: the expected weighted hypervolume improvement criterion. arXiv:1809.05450v1 (2018)
- 9.Fonseca, C.M., Fleming, P.J.: On the performance assessment and comparison of stochastic multiobjective optimizers. In: Voigt, H.-M., Ebeling, W., Rechenberg, I., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 584–593. Springer, Heidelberg (1996). https://doi.org/10.1007/3-540-61723-X_1022CrossRefGoogle Scholar
- 13.Sergeyev, Y., Kvasov, D., Mukhametzhanov, M.: On the efficiency of nature-inspired metaheuristics in expensive global optimization with limited budget. Sci. Rep. 453, 1–8 (2018)Google Scholar