Sharpness-Aware Minimization in Genetic Programming

TL;DR

This paper adapts Sharpness-Aware Minimization (SAM) for Tree Genetic Programming, demonstrating it reduces tree size and redundancy without harming generalization, thus improving evolutionary efficiency.

Contribution

It introduces a novel SAM-based method for TGP that leverages semantic neighborhoods to enhance solution quality and efficiency.

Findings

Significant reduction in tree sizes in TGP populations.

Decrease in redundancy of evolved trees.

No deterioration in generalization ability of solutions.

Abstract

Sharpness-Aware Minimization (SAM) was recently introduced as a regularization procedure for training deep neural networks. It simultaneously minimizes the fitness (or loss) function and the so-called fitness sharpness. The latter serves as a measure of the nonlinear behavior of a solution and does so by finding solutions that lie in neighborhoods having uniformly similar loss values across all fitness cases. In this contribution, we adapt SAM for tree Genetic Programming (TGP) by exploring the semantic neighborhoods of solutions using two simple approaches. By capitalizing upon perturbing input and output of program trees, sharpness can be estimated and used as a second optimization criterion during the evolution. To better understand the impact of this variant of SAM on TGP, we collect numerous indicators of the evolutionary process, including generalization ability, complexity, diversity, and a recently proposed genotype-phenotype mapping to study the amount of redundancy in trees. The experimental results demonstrate that using any of the two proposed SAM adaptations in TGP allows (i) a significant reduction of tree sizes in the population and (ii) a decrease in redundancy of the trees. When assessed on real-world benchmarks, the generalization ability of the elite solutions does not deteriorate.