Paper Info
Title
Learning factorizations in estimation of distribution algorithms using affinity propagation.
Abstract
Estimation of distribution algorithms (EDAs) that use marginal product model factorizations have been widely applied to a broad range of mainly binary optimization problems. In this paper, we introduce the affinity propagation EDA (AffEDA) which learns a marginal product model by clustering a matrix of mutual information learned from the data using a very efficient message-passing algorithm known as affinity propagation. The introduced algorithm is tested on a set of binary and nonbinary decomposable functions and using a hard combinatorial class of problem known as the HP protein model. The results show that the algorithm is a very efficient alternative to other EDAs that use marginal product model factorizations such as the extended compact genetic algorithm (ECGA) and improves the quality of the results achieved by ECGA when the cardinality of the variables is increased.
Year
DOI
Venue
2010
10.1162/EVCO_a_00002
Evolutionary Computation
Keywords
Field
DocType
efficient message-passing algorithm,marginal product model,efficient alternative,broad range,affinity propagation,binary optimization problem,distribution algorithm,extended compact genetic algorithm,use marginal product model,hp protein model,estimation of distribution algorithms,distributed algorithm,mutual information,optimization problem,estimation of distribution algorithm
EDAS,Mathematical optimization,Estimation of distribution algorithm,Affinity propagation,Cardinality,Artificial intelligence,Mutual information,Combinatorial class,Cluster analysis,Machine learning,Genetic algorithm,Mathematics
Journal
Volume
Issue
ISSN
18
4
1530-9304
Citations 
PageRank 
References 
12
0.59
20
Authors
3
Name
Order
Citations
PageRank
Roberto Santana135719.04
Pedro Larrañaga23882208.54
José A. Lozano32148167.25