Improved sampling using loopy belief propagation for probabilistic model building genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Sato:2015:SEC,

• author = "Hiroyuki Sato and Yoshihiko Hasegawa and Danushka Bollegala and Hitoshi Iba",
• title = "Improved sampling using loopy belief propagation for probabilistic model building genetic programming",
• journal = "Swarm and Evolutionary Computation",
• year = "2015",
• volume = "23",
• pages = "1--10",
• month = aug,
• keywords = "genetic algorithms, genetic programming, Estimation of distribution algorithms, Loopy belief propagation, Probabilistic model building GP",
• ISSN = "2210-6502",
• URL = "http://danushka.net/papers/Sato_2015.pdf",
• DOI = "doi:10.1016/j.swevo.2015.02.002",
• URL = "http://www.sciencedirect.com/science/article/pii/S2210650215000176",
• size = "10 pages",
• abstract = "In recent years, probabilistic model building genetic programming (PMBGP) for program optimisation has attracted considerable interest. PMBGPs generally use probabilistic logic sampling (PLS) to generate new individuals. However, the generation of the most probable solutions (MPSs), i.e., solutions with the highest probability, is not guaranteed. In the present paper, we introduce loopy belief propagation (LBP) for PMBGPs to generate MPSs during the sampling process. We selected program optimization with linkage estimation (POLE) as the foundation of our approach and we refer to our proposed method as POLE-BP. We apply POLE-BP and existing methods to three benchmark problems to investigate the effectiveness of LBP in the context of PMBGPs, and we describe detailed examinations of the behaviours of LBP. We find that POLE-BP shows better search performance with some problems because LBP boosts the generation of building blocks.",

}

Genetic Programming entries for Hiroyuki Sato Yoshihiko Hasegawa Danushka Bollegala Hitoshi Iba

Citations