一种通用马尔可夫链建模方法用于(1,λ)-ES线性优化:技术报告
A Generalized Markov-Chain Modelling Approach to $(1,λ)$-ES Linear Optimization: Technical Report
AI总结:
本文提出一种通用马尔可夫链建模方法,用于(1,λ)-ES在线性优化中的应用,探讨了固定步长下常数步长(1,λ)-ES在简单线性约束问题中的成功条件。
摘要:
近年来,有几篇论文研究了(1,λ)-ES对线性优化的马尔可夫链建模,涵盖了无约束和线性约束优化,以及固定和变化的步长。所有研究都假设涉及的随机步长服从正态分布,尽管这与黑盒场景一致,但利用其他分布可能利用函数优化信息(例如分离性)。本文的目标是补充之前使用正态步长的研究,并为常数步长(1,λ)-ES在简单线性函数线性约束问题中的成功提供充分条件。将多维分布分解为其边缘分布和结合它们的copula应用于新的分布假设,特别关注具有阿基米得copula分布的分布。
英文摘要:
Several recent publications investigated Markov-chain modelling of linear optimization by a $(1,λ)$-ES, considering both unconstrained and linearly constrained optimization, and both constant and varying step size. All of them assume normality of the involved random steps, and while this is consistent with a black-box scenario, information on the function to be optimized (e.g. separability) may be exploited by the use of another distribution. The objective of our contribution is to complement previous studies realized with normal steps, and to give sufficient conditions on the distribution of the random steps for the success of a constant step-size $(1,λ)$-ES on the simple problem of a linear function with a linear constraint. The decomposition of a multidimensional distribution into its marginals and the copula combining them is applied to the new distributional assumptions, particular attention being paid to distributions with Archimedean copulas.
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。