eometric semantic genetic programming (GSGP) is a well-known variant of genetic programming (GP) where recombination and mutation operators have a clear semantic effect. Both kind of operators have randomly selected parameters that are not optimized by the search process. In this paper we combine GSGP with a well-known gradient-based optimizer, Adam, in order to leverage the ability of GP to operate structural changes of the individuals with the ability of gradient-based methods to optimize the parameters of a given structure. Two methods, named HYB-GSGP and HeH-GSGP, are defined and compared with GSGP on a large set of regression problems, showing that the use of Adam can improve the performance on the test set. The idea of merging evolutionary computation and gradient-based optimization is a promising way of combining two methods with very different – and complementary – strengths.

Combining Geometric Semantic GP with??Gradient-Descent Optimization

Gloria Pietropolli;Luca Manzoni;Alessia Paoletti;
2022

Abstract

eometric semantic genetic programming (GSGP) is a well-known variant of genetic programming (GP) where recombination and mutation operators have a clear semantic effect. Both kind of operators have randomly selected parameters that are not optimized by the search process. In this paper we combine GSGP with a well-known gradient-based optimizer, Adam, in order to leverage the ability of GP to operate structural changes of the individuals with the ability of gradient-based methods to optimize the parameters of a given structure. Two methods, named HYB-GSGP and HeH-GSGP, are defined and compared with GSGP on a large set of regression problems, showing that the use of Adam can improve the performance on the test set. The idea of merging evolutionary computation and gradient-based optimization is a promising way of combining two methods with very different – and complementary – strengths.
978-3-031-02055-1
978-3-031-02056-8
https://link.springer.com/chapter/10.1007/978-3-031-02056-8_2
File in questo prodotto:
File Dimensione Formato  
Eric-Medvet-_editor__-Gisele-Pappa-_editor__-Bing-Xue-_editor_-Genetic-Programming_-25th-European-Co-40-61.pdf

non disponibili

Licenza: Copyright dell'editore
Dimensione 2.35 MB
Formato Adobe PDF
2.35 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11368/3029181
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact