arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.04707math.OCcs.NE
收藏

平均策略的渐近收敛速度

Asymptotic convergence rates for averaging strategies

Laurent Meunier, Iskander Legheraba, Yann Chevaleyre, Olivier Teytaud

摘要:

并行黑盒优化包括使用$f$的$λ$并行评估来估计函数的最优值。众所周知,对$λ$评估中的$μ$最佳个体进行平均可以比仅仅选择最佳个体更好地估计函数的最优值。在连续域中,该平均通常仅基于(可能加权的)算术平均。以前的理论结果是基于二次目标函数。本文将这一结果推广到更广的一类函数,其中包含三次连续可微函数且具有唯一最优性。我们证明了形式收敛速率,并表明他们确实优于纯随机搜索渐近$λ$。我们验证了我们的理论研究结果与实验上的一些标准的黑盒功能。

英文摘要:

Parallel black box optimization consists in estimating the optimum of a function using $λ$ parallel evaluations of $f$. Averaging the $μ$ best individuals among the $λ$ evaluations is known to provide better estimates of the optimum of a function than just picking up the best. In continuous domains, this averaging is typically just based on (possibly weighted) arithmetic means. Previous theoretical results were based on quadratic objective functions. In this paper, we extend the results to a wide class of functions, containing three times continuously differentiable functions with unique optimum. We prove formal rate of convergences and show they are indeed better than pure random search asymptotically in $λ$. We validate our theoretical findings with experiments on some standard black box functions.

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。

↑