We establish global convergence of the (1+1) evolution strategy, i.e., convergence to a critical point independent of the initial state. More precisely, we show the existence of a critical limit point, using a suitable extension of the notion of a critical point to measurable functions. At its core, the analysis is based on a novel progress guarantee for elitist, rank-based evolutionary algorithms. By applying it to the (1+1) evolution strategy we are able to provide an accurate characterization of whether global convergence is guaranteed with full probability, or whether premature convergence is possible. We illustrate our results on a number of example applications ranging from smooth (non-convex) cases over different types of saddle points and ridge functions to discontinuous and extremely rugged problems.
翻译:我们建立了1+1进化战略的全球趋同,即与初始状态无关的关键点相趋同。更准确地说,我们用一个临界点概念的适当延伸,将一个临界点的概念与可衡量的功能相匹配,从而表明存在一个关键限制点。从本质上说,分析的基础是对精英、按等级划分的进化算法的新的进展保障。通过将其应用于1+1进化战略,我们能够准确描述全球趋同是否完全有可能得到保障,或者是否可能过早趋同。我们举例说明了我们在若干应用方面的结果,从对不同类型的搭载点和脊柱功能的平稳(非混凝固)案例到不连续和极其棘手的问题。