Diagnostic Assessment of Search Controls and Failure Modes in Many-Objective Evolutionary Optimization

• Published in: Evolutionary computation Vol. 20; no. 3; pp. 423 - 452
• Main Authors: Hadka, David, Reed, Patrick
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.09.2012
• Subjects: Algorithms; Assessments; Control equipment; Controllability; Diagnostic systems; Evolutionary algorithms; Evolutionary computation; Failure modes; many-objective optimization; multiobjective optimization; Optimization; parameterization; search control; Searching
• ISSN: 1063-6560; 1530-9304; 1530-9304
• DOI: 10.1162/EVCO_a_00053

The growing popularity of multiobjective evolutionary algorithms (MOEAs) for solving many-objective problems warrants the careful investigation of their search controls and failure modes. This study contributes a new diagnostic assessment framework for rigorously evaluating the effectiveness, reliability, efficiency, and controllability of MOEAs as well as identifying their search controls and failure modes. The framework is demonstrated using the recently introduced Borg MOEA, -NSGA-II, -MOEA, IBEA, OMOPSO, GDE3, MOEA/D, SPEA2, and NSGA-II on 33 instances of 18 test problems from the DTLZ, WFG, and CEC 2009 test suites. The diagnostic framework exploits Sobol's variance decomposition to provide guidance on the algorithms’ non-separable, multi-parameter controls when performing a many-objective search. This study represents one of the most comprehensive empirical assessments of MOEAs ever completed.