Runtime phylogenetic analysis enables extreme subsampling for test-based problems

TL;DR

This paper introduces phylogeny-informed subsampling methods that leverage runtime phylogenetic analysis to improve problem-solving success in genetic programming, especially under extreme subsampling conditions.

Contribution

It presents novel phylogeny-informed subsampling techniques that outperform traditional methods at extreme subsampling levels in evolutionary search problems.

Findings

Enables success at extreme subsampling levels where other methods fail.

Improves diversity maintenance compared to random subsampling.

Shows variable effects on exploiting fitness gradients depending on the selection scheme.

Abstract

A phylogeny describes the evolutionary history of an evolving population. Evolutionary search algorithms can perfectly track the ancestry of candidate solutions, illuminating a population's trajectory through the search space. However, phylogenetic analyses are typically limited to post-hoc studies of search performance. We introduce phylogeny-informed subsampling, a new class of subsampling methods that exploit runtime phylogenetic analyses for solving test-based problems. Specifically, we assess two phylogeny-informed subsampling methods -- individualized random subsampling and ancestor-based subsampling -- on three diagnostic problems and ten genetic programming (GP) problems from program synthesis benchmark suites. Overall, we found that phylogeny-informed subsampling methods enable problem-solving success at extreme subsampling levels where other subsampling methods fail. For example, phylogeny-informed subsampling methods more reliably solved program synthesis problems when evaluating just one training case per-individual, per-generation. However, at moderate subsampling levels, phylogeny-informed subsampling generally performed no better than random subsampling on GP problems. Our diagnostic experiments show that phylogeny-informed subsampling improves diversity maintenance relative to random subsampling, but its effects on a selection scheme's capacity to rapidly exploit fitness gradients varied by selection scheme. Continued refinements of phylogeny-informed subsampling techniques offer a promising new direction for scaling up evolutionary systems to handle problems with many expensive-to-evaluate fitness criteria.