Biobjective Performance Assessment with the COCO Platform

Dimo Brockhoff (1) , Tea Tušar (1) , Dejan Tusar (1) , Tobias Wagner (2) , Nikolaus Hansen (3) , Anne Auger (3)

1 DOLPHIN - Parallel Cooperative Multi-criteria Optimization
2 TU - Technische Universität Dortmund [Dortmund]
3 TAO - Machine Learning and Optimisation

This document details the rationales behind assessing the performance of numerical black-box optimizers on multi-objective problems within the COCO platform and in particular on the biobjective test suite bbob-biobj. The evaluation is based on a hypervolume of all non-dominated solutions in the archive of candidate solutions and measures the runtime until the hypervolume value succeeds prescribed target values.

Domaines: Réseau de neurones [cs.NE]; Apprentissage [cs.LG]; Analyse numérique [cs.NA]; Logiciel mathématique [cs.MS]; Performance et fiabilité [cs.PF]

Dimo Brockhoff, Tea Tušar, Dejan Tusar, Tobias Wagner, Nikolaus Hansen, et al.. Biobjective Performance Assessment with the COCO Platform. 2016. ⟨hal-01315317⟩