Multi-objective Go with the Winners Algorithm: A Preliminary Study

This paper introduces a new algorithm to deal with multiobjective combinatorial and continuous problems. The algorithm is an extension of a previous one designed to deal with single objective combinatorial problems. The original purpose of the single objective version was to study in a rigorous way the properties the search graph of a particular problem needs to hold so that a randomized local search heuristic will find the optimum with high probability. The extension of these results to better understand multi-objective combinatorial problems seems to be a promising line of research. The work presented here is a first small step in this direction. A detailed description of the multi-objective version is presented along with preliminary experimental results on a well known combinatorial problem. The results show that the algorithm has the desired characteristics.