Adaptive ε-Ranking on many-objective problems

This work proposes Adaptive ε-Ranking to enhance Pareto based selection, aiming to develop effective many -objective evolutionary optimization algorithms. ε-Ranking fine grains ranking of solutions after they have been ranked by Pareto dominance, using a randomized sampling procedure combined with ε...

Full description

Saved in:
Bibliographic Details
Published in:Evolutionary intelligence Vol. 2; no. 4; pp. 183 - 206
Main Authors: Aguirre, Hernán, Tanaka, Kiyoshi
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer-Verlag 01.12.2009
Subjects:
Applications of Mathematics
Artificial Intelligence
Bioinformatics
Control
Engineering
Mathematical and Computational Engineering
Mechatronics
Robotics
Special Issue
Statistical Physics and Dynamical Systems
Epistasis
Many-objective optimization
Selection
ε-Ranking
Adaptation
ISSN:1864-5909, 1864-5917
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work proposes Adaptive ε-Ranking to enhance Pareto based selection, aiming to develop effective many -objective evolutionary optimization algorithms. ε-Ranking fine grains ranking of solutions after they have been ranked by Pareto dominance, using a randomized sampling procedure combined with ε-dominance to favor a good distribution of the samples. In the proposed method, sampled solutions keep their initial rank and solutions located within the virtually expanded ε-dominance regions of the sampled solutions are demoted to an inferior rank. The parameter ε that determines the expanded regions of dominance of the sampled solutions is adapted at each generation so that the number of best-ranked solutions is kept close to a desired number that is expressed as a fraction of the population size. We enhance NSGA-II with the proposed method and analyze its performance on MNK-Landscapes, showing that the adaptive method works effectively and that compared to NSGA-II convergence and diversity of solutions can be improved remarkably on MNK-Landscapes with 3 ≤  M  ≤ 10 objectives. Also, we compare the performance of Adaptive ε-Ranking with two representative many-objective evolutionary algorithms on DTLZ continuous functions. Results on DTLZ functions with 3 ≤  M  ≤ 10 objectives suggest that the three many-objective approaches emphasize different areas of objective space and could be used as complementary strategies to produce a better approximation of the Pareto front.
ISSN:1864-5909
1864-5917
DOI:10.1007/s12065-009-0031-2