arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.03336cs.NE
收藏

快速扰动算法配置器

Fast Perturbative Algorithm Configurators

George T. Hall, Pietro Simone Oliveto, Dirk Sudholt

摘要:

最近的工作表明,ParamRLS和ParamILS算法配置器可以在参数空间大小的线性预期时间内为标准基准函数调整一些简单的随机搜索算法。在本文中,我们证明了一个线性下界的预期时间,以优化任何参数调整问题的ParamRLS,ParamILS以及较大类的算法配置。我们提出了一种用于微扰算法配置器的调和变异算子,该算子可证明地在多对数时间内为单峰和近似单峰(即,非平滑的、具有朝向最优的潜在梯度的粗糙的)参数空间。它适合作为通用运算符,因为即使在最坏情况下(例如,欺骗性的)景观,它最多只比ParamRLS和ParamILS使用的默认值慢一个对数因子。实验分析证实了在实践中的一些配置方案,包括涉及多个参数的方法的优越性。

英文摘要:

Recent work has shown that the ParamRLS and ParamILS algorithm configurators can tune some simple randomised search heuristics for standard benchmark functions in linear expected time in the size of the parameter space. In this paper we prove a linear lower bound on the expected time to optimise any parameter tuning problem for ParamRLS, ParamILS as well as for larger classes of algorithm configurators. We propose a harmonic mutation operator for perturbative algorithm configurators that provably tunes single-parameter algorithms in polylogarithmic time for unimodal and approximately unimodal (i.e., non-smooth, rugged with an underlying gradient towards the optimum) parameter spaces. It is suitable as a general-purpose operator since even on worst-case (e.g., deceptive) landscapes it is only by at most a logarithmic factor slower than the default ones used by ParamRLS and ParamILS. An experimental analysis confirms the superiority of the approach in practice for a number of configuration scenarios, including ones involving more than one parameter.

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。

↑