RM-MEDA: A Regularity Model-Based Multiobjective Estimation of Distribution Algorithm

Under mild conditions, it can be induced from the Karush-Kuhn-Tucker condition that the Pareto set, in the decision space, of a continuous multiobjective optimization problem is (m - 1)-D piecewise continuous, where m is the number of objectives. Based on this regularity property, we propose a Regularity Model based Multiobjective Estimation of Distribution Algorithm (RM-MEDA) for continuous multiobjective optimization problems with variable linkages. At each generation, the proposed algorithm models a promising area in the decision space by a probability distribution whose centroid is a (m-1)-D piecewise continuous manifold. The Local Principal Component Analysis algorithm is used for building such a model. New trial solutions are sampled from the model thus built. A nondominated sorting based selection is used for choosing solutions for the next generation. Systematic experiments have shown that, overall, RM-MEDA outperforms three other state-of-theart algorithms, namely, GDE3, PCX-N...

• Type: Journal
• Year: 2008
• Where: TEC
• Authors: Qingfu Zhang, Aimin Zhou, Yaochu Jin
• Keywords: Continuous Multiobjective Optimization, Multiobjective Optimization Problems, TEC 2008, Variable Linkages