id: 05829036
dt: a
an: 05829036
au: Bartz-Beielstein, Thomas; Preuss, Mike
ti: The future of experimental research.
so: Bartz-Beielstein, Thomas (ed.) et al., Experimental methods for the
    analysis of optimization algorithms. With forewords by Catherine C.
    McGeoch and Hans Paul Schwefel. Berlin: Springer (ISBN
    978-3-642-02537-2/hbk; 978-3-642-02538-9/ebook). 17-49 (2010).
py: 2010
pu: Berlin: Springer
la: EN
cc: 
ut: metaheuristic methods; sequential parameter optimization method
ci: 
li: doi:10.1007/978-3-642-02538-9_2
ab: Summary: In the experimental analysis of metaheuristic methods, two issues
    are still not sufficiently treated. Firstly, the performance of
    algorithms depends on their parametrizations-and of the
    parametrizations of the problem instances. However, these dependencies
    can be seen as means for understanding an algorithm’s behavior.
    Secondly, the nondeterminism of evolutionary and other metaheuristic
    methods renders result distributions, not numbers. Based on the
    experience of several tutorials on the matter, we provide a
    comprehensive, effective, and very efficient methodology for the design
    and experimental analysis of metaheuristics such as evolutionary
    algorithms. We rely on modern statistical techniques for tuning and
    understanding algorithms from an experimental perspective. Therefore,
    we make use of the sequential parameter optimization method that has
    been successfully applied as a tuning procedure to numerous heuristics
    for practical and theoretical optimization problems.
rv: