无导数优化的查询复杂性
Query Complexity of Derivative-Free Optimization
摘要:
本文提供了无导数优化(DFO)的收敛速度与噪声函数评估的下限,暴露了一个基本的和不可避免的差距与访问梯度的算法的性能和那些只访问函数评估。然而,也有DFO是不可避免的情况下,对于这种情况下,我们提出了一个新的DFO算法,被证明是接近最优的一类强凸目标函数。该算法的一个显著特点是它只使用布尔值函数比较,而不是函数求值。这使得该算法在更广泛的应用中是有用的,例如基于来自人类受试者的配对比较的优化。我们还表明,无论DFO是基于噪声函数的评价或布尔值函数的比较,收敛速度是相同的。
英文摘要:
This paper provides lower bounds on the convergence rate of Derivative Free Optimization (DFO) with noisy function evaluations, exposing a fundamental and unavoidable gap between the performance of algorithms with access to gradients and those with access to only function evaluations. However, there are situations in which DFO is unavoidable, and for such situations we propose a new DFO algorithm that is proved to be near optimal for the class of strongly convex objective functions. A distinctive feature of the algorithm is that it uses only Boolean-valued function comparisons, rather than function evaluations. This makes the algorithm useful in an even wider range of applications, such as optimization based on paired comparisons from human subjects, for example. We also show that regardless of whether DFO is based on noisy function evaluations or Boolean-valued function comparisons, the convergence rate is the same.
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。