Correlation of Problem Hardness and Fitness Landscapes in the Quadratic Assignment Problem

Abstract

Estimating hardness based on intrinsic characteristics of problem instances plays an important role in algorithm selection and parameter tuning. We have compiled an extensive study of different fitness landscape and problem specific measures for the quadratic assignment problem to predict and correlate problem instance hardness for several different algorithms. We combine different fitness landscape measures that provide a generally applicably problem characterization independent of problem class with problem specific measures that have been defined for the quadratic assignment problem specifically. These measures are used to create separate and combined regression models for several different hardness measures of several different metaheuristic algorithms and are compared against each other.