Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2402.01610 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913221533761536 |
|---|---|
| author | Lalejini, Alexander Sanson, Marcos Garbus, Jack Moreno, Matthew Andres Dolson, Emily |
| author_facet | Lalejini, Alexander Sanson, Marcos Garbus, Jack Moreno, Matthew Andres Dolson, Emily |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01610 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Runtime phylogenetic analysis enables extreme subsampling for test-based problems Lalejini, Alexander Sanson, Marcos Garbus, Jack Moreno, Matthew Andres Dolson, Emily Neural and Evolutionary Computing 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. |
| title | Runtime phylogenetic analysis enables extreme subsampling for test-based problems |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2402.01610 |