How to do multi-objective optimization?
the information for the operator "ClassificationPerformance" says "that for true multi-objective optimization usually another selection scheme is used instead of simply replacing the performance comparator".
Does it suffice for *true* multi-objective optimization to choose "non dominated sorting" as the selection scheme in evolutionary operators like EvolutionaryParameterOptimization? For example, could I implement my own performance criteria, put them in a performance vector and optimize for both criteria at the same time by just using the standard evolutionary paramter optimization with the aforementioned selection scheme?
Greetings and thanks for any help in advance