Data for GECCO2023 Paper "Many-objective (Combinatorial) Optimization is Easy"
DOI10.5281/zenodo.7625398Zenodo7625398MaRDI QIDQ6699512FDOQ6699512
Dataset published at Zenodo repository.
Arnaud Liefooghe, Manuel López-Ibáñez
Publication date: 15 July 2023
Copyright license: Creative Commons Attribution 4.0 International
Data for Paper Many-objective (Combinatorial) Optimization is Easy instances.tar.xz contains 𝜌mnk-landscape instances metrics.csv contains the metric-values based on full enumeration performance.csv contains the Pareto resolution and the hypervolume of the different algorithms one each instance performance_neval.csv contains the number of evaluations performed by PLS script.R is the R scriptfor producing the figures Reference Arnaud Liefooghe and Manuel Lpez-Ibez. 2023. Many-objective (Combinatorial) Optimization is Easy. In Genetic and Evolutionary Computation Conference (GECCO 23), July 1519, 2023, Lisbon, Portugal. https://doi.org/10.1145/3583131.3590475 Abstract It is a common held assumption that problems with many objectives are harder to optimize than problems with two or three objectives. In this paper, we challenge this assumption and provide empirical evidence that increasing the number of objectives tends to reduce the difficulty of the landscape being optimized. Of course, increasing the number of objectives brings about other challenges, such as an increase in the computational effort of many operations, or the memory requirements for storing non-dominated solutions. More precisely, we consider a broad range of multi- and many-objective combinatorial benchmark problems, and we measure how the number of objectives impacts the dominance relation among solutions, the connectedness of the Pareto set, and the landscape multimodality in terms of local optimal solutions and sets. Our analysis shows the limit behavior of various landscape features when adding more objectives to a problem. Our conclusions do not contradict previous observations about the inability of Pareto-optimality to drive search, but we explain these observations from a different perspective. Our findings have important implications for the design and analysis of many-objective optimization algorithms.
This page was built for dataset: Data for GECCO2023 Paper "Many-objective (Combinatorial) Optimization is Easy"
