Compact Optimization Algorithms with Re-sampled Inheritance
Compact optimization algorithms are a class of Estimation of Distribution Algorithms (EDAs) characterized by extremely limited memory requirements (hence they are called \compact"). As all EDAs, compact algorithms build and update a probabilistic model of the distribution of solutions within the search space, as opposed to population-based algorithms that instead make use of an explicit population of solutions. In addition to that, to keep their memory consumption low, compact algorithms purposely employ simple probabilistic models that can be described with a small number of parameters. Despite their simplicity, compact algorithms have shown good performances on a broad range of benchmark functions and real-world problems. However, compact algorithms also come with some drawbacks, i.e. they tend to premature convergence and show poorer performance on non-separable problems. To overcome these limitations, here we investigate a possible algorithmic scheme obtained by combining compact algorithms with a non-disruptive restart mechanism taken from the literature, named Re-Sampled Inheritance (RI). The resulting compact algorithms with RI are tested on the CEC 2014 benchmark functions. The numerical results show on the one hand that the use of RI consistently enhances the performances of compact algorithms, still keeping a limited usage of memory. On the other hand, our experiments show that among the tested algorithms, the best performance is obtained by compact Differential Evolution with RI.
The file attached to this record is the author's final peer reviewed version.
Citation : Iacca, G. and Caraffini, F. (2019) Compact Optimization Algorithms with Re-sampled Inheritance. In: Kaufmann, P. and Castillo, P. (Eds) Proceedings of Applications of Evolutionary Computation, EvoApplications 2019, 22nd International Conference on the Applications of Evolutionary Computation, Leipzig, Germany, April 2019.
ISSN : 0302-9743
Research Group : Institute of Artificial Intelligence (IAI)
Research Institute : Institute of Artificial Intelligence (IAI)
Peer Reviewed : Yes