Cooperative Estimation of Distribution Algorithm for Continuous Problems Solving.

Abstract: Since the estimation of distribution algorithm(EDA) was introduced, different approaches for continuous problems solving have been developed. Through the efforts of many scholars, the EDAs brought some success in continuous domain, but there are still some deficiencies: Gaussian-based EDA doesn’t perform well in problems with many optima, such as Schwefel function; histogram-based EDA doesn’t perform well in problems with singular global optimum, such as Three-Peak function. Because of this, based on improved histogram-based EDA and referred to the idea of k-Means clustering, we built cooperative EDA. Experimental results showed that the improved algorithm in this paper can give comparable with or better performance than those improved algorithms. [Copyright &y& Elsevier]