arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.07280math.OCcs.MAcs.SYeess.SY
收藏

鲁棒单调子模函数最大化

Resilient Monotone Submodular Function Maximization

University of Pennsylvania(宾夕法尼亚大学);Massachusetts Institute of Technology(麻省理工学院)

Vasileios Tzoumas, Konstantinos Gatsis, Ali Jadbabaie, George J. Pappas

AI总结:

本文提出一种基于曲率的可扩展算法,用于解决在对抗性 denial-of-service 攻击或故障下的鲁棒单调子模函数最大化问题,针对低曲率函数提供更优近似性能。

摘要:

本文聚焦于机器学习、优化和控制领域中对少数元素(如特征、传感器或领导者)的鲁棒选择应用。此类鲁棒优化问题通常难以求解,即使目标函数是单调和子模的,也无法在多项式时间内精确求解。然而,本文提出了首个基于曲率的可扩展算法,能够处理任意数量的对抗性 denial-of-service 攻击或故障,并且对于曲率较低的函数,能够保证更优的近似性能。值得注意的是,曲率已被证实能收紧非鲁棒最大化问题的近似效果,但其对鲁棒最大化的影响此前尚不清楚。我们通过理论分析和实证评估进一步支持了这一结论。

英文摘要:

In this paper, we focus on applications in machine learning, optimization, and control that call for the resilient selection of a few elements, e.g. features, sensors, or leaders, against a number of adversarial denial-of-service attacks or failures. In general, such resilient optimization problems are hard, and cannot be solved exactly in polynomial time, even though they often involve objective functions that are monotone and submodular. Notwithstanding, in this paper we provide the first scalable, curvature-dependent algorithm for their approximate solution, that is valid for any number of attacks or failures, and which, for functions with low curvature, guarantees superior approximation performance. Notably, the curvature has been known to tighten approximations for several non-resilient maximization problems, yet its effect on resilient maximization had hitherto been unknown. We complement our theoretical analyses with supporting empirical evaluations.

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。

↑