Lorenzo Canonne
PhD student at Inria
The field of gray box optimization has led to the design of new operators capable of using the structural information of problems; these operators are now the basis of powerful
meta-heuristics. For large-scale NK landscapes, many operators have been proposed and iterated local search combined with gray box crossovers is now the state of the art. However, the literature still lacks a detailed study of the impact of the combination of the different components: perturbation, escape mechanism, crossover or local search. Our goal is to propose a thorough analysis and a recommendation system to propose the best configuration given the available landscape information. Furthermore, we plan to develop static hybrid algorithms using supervised learning and to go further by exploring an adaptive approach to design algorithms able to evolve throughout the execution to propose the most promising algorithm configuration at each iteration.
Keywords: Computational Intelligence, Combinatorial optimisation, Gray-box, Adaptative Algorithms.