The Effects of Population Size on the Performance of BEAGLE GPU-Based Genetic Programming Runs

TL;DR

This paper investigates how different GPU-based population sizes in genetic programming affect training success for symbolic regression, revealing benefits of both narrow and broad searches and proposing stepped population strategies.

Contribution

It provides empirical insights into population size effects on GPU-based genetic programming and introduces stepped population approaches for improved search balance.

Findings

Narrow, deep searches benefit some problems.

Broad, shallow searches benefit others.

Stepped population sizes balance search breadth and depth.

Abstract

The Beagle framework, through GPU-based Genetic Programming, enables population dynamics previously unattainable (within practical time frames) by CPU-constrained Genetic Programming systems. This work explores how GPU-enabled population sizes impact the success of training for symbolic regression problems. Specifically, when using constant population sizes, we see benefits of using very narrow and deep searches (as narrow as 1000 individuals) for some problems, while other problems benefit from very broad and shallow searches (as broad as 10 million individuals). We also explore stepped population sizes that start with large populations and drop to small populations to balance the breadth and depth of search.