arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09344math.OC
收藏

组合结构鞍点问题的加速算法

On Accelerated Methods for Saddle-Point Problems with Composite Structure

Vladislav Tominin, Yaroslav Tominin, Ekaterina Borodich, Dmitry Kovalev, Alexander Gasnikov, Pavel Dvurechensky

摘要:

考虑了具有一般非双线性目标函数的强凸-强凹鞍点问题,其原始变量和对偶变量具有不同的条件数。首先,我们考虑这样的问题与光滑的复合项,其中之一具有有限和结构。对于这种设置,我们提出了一个方差降低算法的复杂性估计优于现有的界限在文献中。其次,我们考虑了有限和鞍点问题的复合项,并提出了几个算法取决于复合项的性质。当复合项是光滑的,我们得到更好的复杂性界比文献中的,包括最近提出的近最优算法,不考虑复合结构的问题的界限。如果复合条款是友好的,我们提出了一个方差减少算法,一方面,加速相比,现有的方差减少算法,另一方面,在复合设置类似的复杂性范围内的接近最佳的算法,这是专为非复合设置。除此之外,我们的算法允许分离的复杂性界限,即估计,分别为目标的每一部分,Oracle调用的数量,足以达到给定的精度。这是重要的,因为不同的部分可以具有不同的算术复杂度的预言机,并且期望调用昂贵的预言机比调用廉价的预言机更少。所有这些结果的关键是我们的鞍点问题的一般框架,这可能是独立的利益。这个框架,反过来是基于我们提出的加速元算法的复合优化与概率不精确的预言和概率不精确的最接近的映射,这可能是独立的利益,以及。

英文摘要:

We consider strongly-convex-strongly-concave saddle-point problems with general non-bilinear objective and different condition numbers with respect to the primal and the dual variables. First, we consider such problems with smooth composite terms, one of which having finite-sum structure. For this setting we propose a variance reduction algorithm with complexity estimates superior to the existing bounds in the literature. Second, we consider finite-sum saddle-point problems with composite terms and propose several algorithms depending on the properties of the composite terms. When the composite terms are smooth we obtain better complexity bounds than the ones in the literature, including the bounds of a recently proposed nearly-optimal algorithms which do not consider the composite structure of the problem. If the composite terms are prox-friendly, we propose a variance reduction algorithm that, on the one hand, is accelerated compared to existing variance reduction algorithms and, on the other hand, provides in the composite setting similar complexity bounds to the nearly-optimal algorithm which is designed for non-composite setting. Besides that, our algorithms allow to separate the complexity bounds, i.e. estimate, for each part of the objective separately, the number of oracle calls that is sufficient to achieve a given accuracy. This is important since different parts can have different arithmetic complexity of the oracle, and it is desired to call expensive oracles less often than cheap oracles. The key thing to all these results is our general framework for saddle-point problems, which may be of independent interest. This framework, in turn is based on our proposed Accelerated Meta-Algorithm for composite optimization with probabilistic inexact oracles and probabilistic inexactness in the proximal mapping, which may be of independent interest as well.

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。

↑