Combining Genetic Programming and Particle Swarm Optimization to Simplify Rugged Landscapes Exploration

TL;DR

This paper introduces a hybrid heuristic combining genetic programming and particle swarm optimization to create smooth surrogate models that effectively locate global optima in rugged landscapes, improving optimization performance.

Contribution

It presents a novel GP-FST-PSO surrogate model that enhances global optimization by maintaining landscape features while simplifying the search space.

Findings

Successfully finds global optima in complex landscapes

Produces visual approximations of benchmark functions

Outperforms traditional methods in rugged landscape optimization

Abstract

Most real-world optimization problems are difficult to solve with traditional statistical techniques or with metaheuristics. The main difficulty is related to the existence of a considerable number of local optima, which may result in the premature convergence of the optimization process. To address this problem, we propose a novel heuristic method for constructing a smooth surrogate model of the original function. The surrogate function is easier to optimize but maintains a fundamental property of the original rugged fitness landscape: the location of the global optimum. To create such a surrogate model, we consider a linear genetic programming approach enhanced by a self-tuning fitness function. The proposed algorithm, called the GP-FST-PSO Surrogate Model, achieves satisfactory results in both the search for the global optimum and the production of a visual approximation of the original benchmark function (in the 2-dimensional case).