黑盒复杂性:打破LeadingOnes的$O(n \log n)$障碍
Black-Box Complexity: Breaking the $O(n \log n)$ Barrier of LeadingOnes
摘要:
我们证明了$n$维XOR和置换不变的LeadingOnes函数类的无限制黑盒复杂度是$O(n \log (n) / \log \log n)$。这表明,最近自然看起来$O(n\log n)$约束并不紧。黑盒优化算法导致这个界限可以实现的方式,只有3元无偏变差算子使用。因此,我们的界限也适用于Lehre和Witt最近提出的无偏黑盒复杂度(GECCO 2010)。如果我们施加额外的限制,即黑盒算法不能访问目标值,而只能访问它们的相对顺序(基于排名的黑盒复杂度),则该界限也仍然有效。
英文摘要:
We show that the unrestricted black-box complexity of the $n$-dimensional XOR- and permutation-invariant LeadingOnes function class is $O(n \log (n) / \log \log n)$. This shows that the recent natural looking $O(n\log n)$ bound is not tight. The black-box optimization algorithm leading to this bound can be implemented in a way that only 3-ary unbiased variation operators are used. Hence our bound is also valid for the unbiased black-box complexity recently introduced by Lehre and Witt (GECCO 2010). The bound also remains valid if we impose the additional restriction that the black-box algorithm does not have access to the objective values but only to their relative order (ranking-based black-box complexity).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。