12 Global Search Methods

As previously mentioned in Chapter 10, global search methods investigate a diverse potential set of solutions. In this chapter, two methods (genetic algorithms and simulated annealing) will be discussed in the context of selecting appropriate subsets of features. There are a variety of other global search methods that can also be used, such as particle swarm optimization and simultaneous perturbation stochastic approximation. Spall (2005) and Weise (2011) are comprehensive resources for these types of optimization techniques.

Before proceeding, the naive Bayes classification model will be discussed. This classifier will be used throughout this chapter to demonstrate the global search methodologies.

References

Spall, J. 2005. Simultaneous Perturbation Stochastic Approximation. John Wiley; Sons.

Weise, T. 2011. Global Optimization Algorithms - Theory and Application. www.it-weise.de.