Kumara Sastry

Bayesian optimization algorithm, decision graphs, and Occam’s razor

Pelikan, M., Goldberg, D. E., Sastry, K. (2001). Proceedings of the Genetic and Evolutionary Computation Conference, 519—526. [Full paper - PDF] [Full paper - PS].

Abstract:

This paper discusses the use of various scoring metrics in the Bayesian optimization algorithm (BOA) which uses Bayesian networks to model promising solutions and generate the new ones. The use of decision graphs in Bayesian networks to improve the performance of the BOA is proposed. To favor simple models, a complexity measure is incorporated into the Bayesian-Dirichlet metric for Bayesian networks with decision graphs. The presented algorithms are compared on a number of interesting problems.

Related Posts:

• iBOA: The incremental Bayesian optimization algorithm
• Scalability of the Bayesian optimization algorithm
• Evolutionary algorithms + graphical models = scalable black-box optimization
• Fitness inheritance in the Bayesian optimization algorithm
• Influence of selection and replacement strategies on linkage learning in BOA

Comments are closed.