Fitness Landscape-Based Characterisation of Nature-Inspired Algorithms

TL;DR

This paper uses fitness landscape analysis to compare various nature-inspired algorithms on continuous optimization problems, aiming to identify landscape features that influence algorithm performance.

Contribution

It develops a novel approach for comparing multiple continuous optimization algorithms using fitness landscape generation techniques.

Findings

Different algorithms perform best on landscapes with specific features.

The approach enables prediction of suitable algorithms based on landscape characteristics.

Provides insights into the relationship between landscape features and algorithm effectiveness.

Abstract

A significant challenge in nature-inspired algorithmics is the identification of specific characteristics of problems that make them harder (or easier) to solve using specific methods. The hope is that, by identifying these characteristics, we may more easily predict which algorithms are best-suited to problems sharing certain features. Here, we approach this problem using fitness landscape analysis. Techniques already exist for measuring the "difficulty" of specific landscapes, but these are often designed solely with evolutionary algorithms in mind, and are generally specific to discrete optimisation. In this paper we develop an approach for comparing a wide range of continuous optimisation algorithms. Using a fitness landscape generation technique, we compare six different nature-inspired algorithms and identify which methods perform best on landscapes exhibiting specific features.