To improve the performance of MAMaLGam with respect to the bias-variance trade off problem, two methods based on the addition of noise are proposed. Adding noise that leads to an improvement on an objective function generates a mutation on individuals within the clusters.
Individual contributions slides: here
Full project document: here
S.C. Maree - uncrowded-hypervolume
This repository contains implementations (C++) of different uncrowded-hypervolume based methods for (gradient-free) multi-objective optimization. Using the (uncrowded) hypervolume, multi-objective optimization problems can be formulated as (high-dimensional) single-objective optimization problems, in the hypervolume of a solution sets is optimized. For details, see the corresponding publications/preprints.
The main publication corresponding to this work is
Uncrowded Hypervolume-based Multi-objective Optimization with Gene-pool Optimal Mixing by S.C. Maree, T. Alderliesten, P.A.N. Bosman, 2020 (https://arxiv.org/abs/2004.05068)