Journal
GENETIC PROGRAMMING AND EVOLVABLE MACHINES
Volume 22, Issue 3, Pages 357-381Publisher
SPRINGER
DOI: 10.1007/s10710-021-09400-0
Keywords
Symbolic regression; Gradient boosting; Genetic programming
Funding
- National Institutes of Health (USA) [LM010098, LM012601, AI116794]
Ask authors/readers for more resources
By adding a small number of boosting stages (between 2 and 5) to a symbolic regressor, statistically significant improvements can often be attained across 98 regression datasets. SyRBo serves as a simple add-on that can be easily integrated with existing symbolic regressors to produce beneficial results.
Modifying standard gradient boosting by replacing the embedded weak learner in favor of a strong(er) one, we present SyRBo: symbolic-regression boosting. Experiments over 98 regression datasets show that by adding a small number of boosting stages-between 2 and 5-to a symbolic regressor, statistically significant improvements can often be attained. We note that coding SyRBo on top of any symbolic regressor is straightforward, and the added cost is simply a few more evolutionary rounds. SyRBo is essentially a simple add-on that can be readily added to an extant symbolic regressor, often with beneficial results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available