Evaluation of Population Initialization Methods for Genetic Programming-based Symbolic Regression
For practitioners of GP-based symbolic regression, this work shows that initialization method has negligible impact on final Pareto front quality, given similar initial diversity.
The paper evaluates three random initialization methods and one ESR-based initialization for GP-based symbolic regression, finding no significant differences in accuracy or model complexity across twelve synthetic and one real-world dataset. The initial advantage of ESR disappears after a few generations.
We analyze the effect of optimizing the initial population of genetic programming (GP) for symbolic regression (SR) on the accuracy and complexity of solutions. We compare three well-established random initialization methods as well as initialization with small optimized solutions from exhaustive symbolic regression (ESR) using a GP/SR implementation which is based on the multi-objective evolutionary algorithm NSGA-II. We compare the final Pareto fronts found with each initialization method on twelve synthetic problems of varying complexity and one real-world dataset. We find no significant differences in accuracy or model complexity among the initialization methods. The initial advantage of initialization with ESR disappears after only a few generations. Our results show that, given similar diversity in the initial population, the effect of the initialization method in GP-based symbolic regression on the final Pareto front is negligible.