What can phylogenetic metrics tell us about useful diversity in evolutionary algorithms?

Abstract

It is generally accepted that "diversity" is associated with success in evolutionary algorithms. However, diversity is a broad concept that can be measured and defined in a multitude of ways. To date, most evolutionary computation research has measured diversity using the richness and/or evenness of a particular genotypic or phenotypic property. While these metrics are informative, we hypothesize that other diversity metrics are more strongly predictive of success. Phylogenetic diversity metrics are a class of metrics popularly used in biology, which take into account the evolutionary history of a population. Here, we investigate the extent to which 1) these metrics provide different information than those traditionally used in evolutionary computation, and 2) these metrics better predict the long-term success of a run of evolutionary computation. We find that, in most cases, phylogenetic metrics behave meaningfully differently from other diversity metrics. Moreover, our results suggest that phylogenetic diversity is indeed a better predictor of success.

Artificial selection methods from evolutionary computing show promise for directed evolution of microbes

“…Lexicase selection was originally proposed for test-based genetic programming problems Spector, 2012), but has since produced promising results in a variety of domains (Aenugu & Spector, 2019;La Cava et al, 2016;Metevier et al, 2019;Moore & Stanton, 2017). By randomly permuting the objectives for each parent selection, lexicase selection maintains diversity (E. L. Dolson et al, 2018;Helmuth et al, 2016), which improves search space exploration (Hernandez, Lalejini, & Ofria, 2021) and overall problem-solving success Hernandez, Lalejini, & Dolson, 2021).…”

“…Each digital organism is defined by a sequence of program instructions (its genome) and a set of virtual hardware components used to interpret and express those instructions. The virtual hardware and genetic representation used in this work extends that of (E. Hernandez, Lalejini, & Dolson, 2021). The virtual hardware includes the following components: an instruction pointer indicating the position in the genome currently being executed, sixteen registers for performing computations, sixteen memory stacks, input and output buffers, "scopes" that facilitate modular code execution, and machinery to facilitate self-copying.…”