This paper investigates a curious case of informed initialization technique to solve difficult multi-objective optimization (MOP) problems. The initial population was injected with non-exact (i.e. approximated) nadir objective vectors, which are the boundary solutions of a Pareto optimal front (PF). The algorithm then successively improves those boundary solutions and utilizes them to generate non-dominated solutions targeted to the vicinity of the PF along the way. The proposed technique was ported to a standard Evolutionary Multi-objective Optimization (EMO) algorithm and tested on a wide variety of benchmark MOP problems. The experimental results suggest that the proposed approach is very helpful in achieving extremely fast convergence, especially if an experimenter's goal is to find a set of well distributed trade-off solutions within a fix-budgeted solution evaluations (SEs). The proposed approach also ensures a more focused exploration of the underlying search space.
展开▼