A framework for memetic optimization using variable global and local surrogate models
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special Issue on Emerging Trends in Soft Computing - Memetic Algorithms; Guest Editors: Yew-Soon Ong, Meng-Hiot Lim, Ferrante Neri, Hisao Ishibuchi
Accelerating evolutionary algorithms with Gaussian process fitness function models
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Combining Global and Local Surrogate Models to Accelerate Evolutionary Optimization
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Hi-index | 0.00 |
Many applications in engineering and science rely on the optimization of computationally expensive functions. A successful approach in such scenarios is to couple an evolutionary algorithm with a mathematical model which replaces the expensive function. However, models introduce several difficulties, such as their inherent inaccuracy, and the difficulty of matching a model to a particular problem. To address these issues, this paper proposes a model-based evolutionary algorithm with two main implementations: (a) it combats model inaccuracy with a tailored trust-region approach to manage the model during the search, and to ensure convergence to an optimum of the true expensive function, and (b) during the search it continuously selects an optimal model type out of a set of candidate models, resulting in a model-adaptive optimization search. Extensive performance analysis shows the efficacy of the proposed algorithm.