arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.00523math.OC
收藏

具有不精确 Oracle 的凸极小化问题的精度证书

Accuracy Certificates for Convex Minimization with Inexact Oracle

Egor Gladin, Alexander Gasnikov, Pavel Dvurechensky

AI总结:

本文将凸优化精度证书推广至不精确一阶 Oracle,并为基于多面体的割平面方法给出显式构造,实现在线停止、原始解恢复及紧致目标残差界。

摘要:

凸极小化问题的精度证书允许对近似解的精度进行在线验证,并提供理论上有效的在线停止准则。在求解 Lagrange 对偶问题时,精度证书给出了一种恢复近似原始解并估计其精度的简单方法。本文将精度证书推广到不精确一阶 Oracle 的情形,包括原始问题与 Lagrange 对偶问题对的设置。我们进一步提出了一种显式方法,用于为一大类基于多面体的割平面方法构造精度证书。作为附带结果,我们表明所考虑的割平面方法即使最初设计为配备精确 Oracle,也能在含噪 Oracle 下高效使用。最后,我们通过数值实验说明了所提出证书的作用,突出表明我们的证书为目标残差提供了紧致上界。

英文摘要:

Accuracy certificates for convex minimization problems allow for online verification of the accuracy of approximate solutions and provide a theoretically valid online stopping criterion. When solving the Lagrange dual problem, accuracy certificates produce a simple way to recover an approximate primal solution and estimate its accuracy. In this paper, we generalize accuracy certificates for the setting of inexact first-order oracle, including the setting of primal and Lagrange dual pair of problems. We further propose an explicit way to construct accuracy certificates for a large class of cutting plane methods based on polytopes. As a by-product, we show that the considered cutting plane methods can be efficiently used with a noisy oracle even thought they were originally designed to be equipped with an exact oracle. Finally, we illustrate the work of the proposed certificates in the numerical experiments highlighting that our certificates provide a tight upper bound on the objective residual.

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。

↑