Computing factorized approximations of Pareto-fronts using mNM-landscapes and Boltzmann distributions

TL;DR

This paper introduces a method combining multi-objective NM-landscape models with Boltzmann distributions to approximate Pareto fronts, analyzing how landscape parameters influence the shape of these approximations.

Contribution

It proposes a novel approach integrating NM-landscape models and Boltzmann distributions for Pareto-front approximation in multi-objective optimization.

Findings

The joint effect of NM-landscape parameters and probabilistic factorizations on Pareto front shape.

Demonstrates the effectiveness of the combined model in approximating Pareto fronts.

Provides insights into parameter tuning for better Pareto front approximations.

Abstract

NM-landscapes have been recently introduced as a class of tunable rugged models. They are a subset of the general interaction models where all the interactions are of order less or equal $M$. The Boltzmann distribution has been extensively applied in single-objective evolutionary algorithms to implement selection and study the theoretical properties of model-building algorithms. In this paper we propose the combination of the multi-objective NM-landscape model and the Boltzmann distribution to obtain Pareto-front approximations. We investigate the joint effect of the parameters of the NM-landscapes and the probabilistic factorizations in the shape of the Pareto front approximations.