Fast non-dominated sorting evolutionary algorithm II based on relative non-dominance matrix for portfolio optimization

Convergence and diversity are two crucial aspects for multi-objective optimization. Over past few decades, many researchers have dedicated their efforts to design more efficient convergence mechanisms. Different from them, this article is focused on the further improvement of the diversity preservation. First, a recently proposed relative non-dominance matrix is empirically analyzed. As a result, it is found that the relative non-dominance matrix can be used as a diversity evaluator. Based on the relative non-dominance matrix, this article proposed a new optimizer for multi-objective optimization problems. Experimental results on two popular test suites and a portfolio optimization problem illustrate the superiority of the proposed optimizer over state-of-the-art methods.