Shape-Constrained Symbolic Regression—Improving Extrapolation with Prior Knowledge
Evolutionary Computation · 01.03.2022 · 30 (1) · 75-98
DOI: 10.1162/evco_a_00294 ↗Kurz gefasst
Fachartikel in der Zeitschrift Evolutionary Computation, online erschienen am 01.03.2022. Verfasst von G Kronberger und 4 weiteren Autor:innen. Beteiligte Einrichtung: Josef Ressel Center for Symbolic Regression, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria gabriel.kronberge…. Hauptthemen laut MEDLINE: Algorithms, Biological Evolution. Die Arbeit wurde bisher 79-mal zitiert (Crossref) und nennt 59 Literaturangaben.
Abstract (Originalsprache)
We investigate the addition of constraints on the function image and its derivatives for the incorporation of prior knowledge in symbolic regression. The approach is called shape-constrained symbolic regression and allows us to enforce, for example, monotonicity of the function over selected inputs. The aim is to find models which conform to expected behavior and which have improved extrapolation capabilities. We demonstrate the feasibility of the idea and propose and compare two evolutionary algorithms for shape-constrained symbolic regression: (i) an extension of tree-based genetic programming which discards infeasible solutions in the selection step, and (ii) a two-population evolutionary algorithm that separates the feasible from the infeasible solutions. In both algorithms we use interval arithmetic to approximate bounds for models and their partial derivatives. The algorithms are tested on a set of 19 synthetic and four real-world regression problems. Both algorithms are able to identify models which conform to shape constraints which is not the case for the unmodified symbolic regression algorithms. However, the predictive accuracy of models with constraints is worse on the training set and the test set. Shape-constrained polynomial regression produces the best results for the test set but also significantly larger models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Josef Ressel Center for Symbolic Regression, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria gabriel.kronberger@fh-ooe.at.
- Center for Mathematics, Computation and Cognition (CMCC), Heuristics, Analysis and Learning Laboratory (HAL), Federal University of ABC, Santo Andre, Brazil folivetti@ufabc.edu.br.
- Josef Ressel Center for Symbolic Regression, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria bogdan.burlacu@fh-hagenberg.at.
- Josef Ressel Center for Symbolic Regression, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria christian.haider@fh-hagenberg.at.
- Josef Ressel Center for Symbolic Regression, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria michael.kommenda@fh-hagenberg.at.
Zitieren
APA
Kronberger, G., de Franca, F. O., Burlacu, B., Haider, C., & Kommenda, M. (2022). Shape-Constrained Symbolic Regression—Improving Extrapolation with Prior Knowledge. Evolutionary Computation, 30(1), 75-98. https://doi.org/10.1162/evco_a_00294
Vancouver
Kronberger G, de Franca FO, Burlacu B, Haider C, Kommenda M. Shape-Constrained Symbolic Regression—Improving Extrapolation with Prior Knowledge. Evolutionary Computation. 2022;30(1):75-98. doi:10.1162/evco_a_00294
BibTeX
@article{Kronberger2022,
author = {Kronberger, G and de Franca, F O and Burlacu, B and Haider, C and Kommenda, M},
title = {Shape-Constrained Symbolic Regression—Improving Extrapolation with Prior Knowledge},
journal = {Evolutionary Computation},
year = {2022},
volume = {30},
number = {1},
pages = {75--98},
doi = {10.1162/evco_a_00294}
}
EUVIMED