AI

Theoretical Convergence Guarantees for Cooperative Coevolutionary Algorithms

Abstract

Cooperative coevolutionary algorithms have the potential to significantly speed up the search process by dividing the space into parts that can be each conquered separately. Unfortunately, recent research presented theoretical and empirical arguments that these algorithms might not be fit for optimization tasks, as they might tend to drift to suboptimal solutions in the search space. This paper details an extended formal model for cooperative coevolutionary algorithms, and uses it to demonstrate that these algorithms will converge to the globally optimal solution, if properly set and if given enough resources. We also present an intuitive graphical visualization for the basins of attraction to optimal and suboptimal solutions in the search space.