Manukyan Narine, Eppstein Margaret J, Buzas Jeffrey S
Department of Computer Science, University of Vermont, Burlington, VT 05401 USA.
Department and Mathematics and Statistics, University of Vermont, Burlington, VT 05401 USA.
IEEE Trans Evol Comput. 2016 Apr;20(2):263-274. doi: 10.1109/TEVC.2015.2454857. Epub 2015 Jul 9.
We propose landscapes as a new class of tunably rugged benchmark problems. landscapes are well defined on alphabets of any arity, including both discrete and real-valued alphabets, include epistasis in a natural and transparent manner, are proven to have known value and location of the global maximum and, with some additional constraints, are proven to also have a known global minimum. Empirical studies are used to illustrate that, when coefficients are selected from a recommended distribution, the ruggedness of landscapes is smoothly tunable and correlates with several measures of search difficulty. We discuss why these properties make landscapes preferable to both landscapes and Walsh polynomials as benchmark landscape models with tunable epistasis.
我们提出将景观作为一类新的具有可调崎岖度的基准问题。景观在任何元数的字母表上都有明确的定义，包括离散和实值字母表，以自然且透明的方式包含上位性，已被证明具有已知的全局最大值的数值和位置，并且在一些额外约束下，也被证明具有已知的全局最小值。实证研究用于说明，当系数从推荐分布中选取时，景观的崎岖度是可平滑调节的，并且与几种搜索难度度量相关。我们讨论了为什么这些特性使得景观作为具有可调上位性的基准景观模型比景观和沃尔什多项式更具优势。
