Many real-world optimization problems contain multiple competing objectives and that is why the design of optimization techniques that can scalably discover an optimal tradeoff between given objectives (Pareto-optimal solutions) represents an important challenge. This chapter discusses estimation of distribution algorithms (EDAs) that address this challenge. The primary focus is on scalability on discrete multiobjective decomposable problems and the multiobjective hierarchical BOA (mohBOA); other approaches to the multiobjective EDA design are discussed briefly. © Springer-Verlag Berlin Heidelberg 2006.
CITATION STYLE
Pelikan, M., Sastry, K., & Goldberg, D. E. (2007). Multiobjective estimation of distribution algorithms. Studies in Computational Intelligence, 33, 223–248. https://doi.org/10.1007/978-3-540-34954-9_10
Mendeley helps you to discover research relevant for your work.