In decision-making under uncertainty, several criteria have been studied to aggregate the performance of a solution over multiple possible scenarios. This paper introduces a novel variant of ordered weighted averaging (OWA) for optimization problems. It generalizes the classic OWA approach, which includes robust min-max optimization as a special case, as well as min-max regret optimization. We derive new complexity results for this setting, including insights into the inapproximability and approximability of this problem. In particular, we provide stronger positive approximation results that asymptotically improve the previously best-known bounds for the classic OWA approach. In computational experiments, we evaluate the quality of the proposed methods and compare the proposed setting with classic OWA and min-max regret approaches.
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition
Yale University(耶鲁大学);Simons Institute for the Theory of Computing(西蒙斯理论计算研究所);Massachusetts Institute of Technology(麻省理工学院);University of Southern California(南加利福尼亚大学)
我们研究的问题切换约束在线凸优化(OCO),玩家有有限的机会改变她的行动。虽然这个在线学习任务的离散模拟已被广泛研究,以前的工作在连续设置既没有建立极大极小率,也没有算法实现it.In本文中,我们表明,$ T $轮开关约束OCO少于$ K $开关有极大极小遗憾$ Θ(\frac{T}{\sqrt{K}}) $。特别地,对于一维,其至少为$ \frac{T}{\sqrt{2K}} $,对于更高维度,其至少为$ \frac{T}{\sqrt{K}} $。在高维的下界是通过一个正交子空间的论点。在一维中,一种新的对抗策略产生了$O(\frac{T}{\sqrt{K}})$的下界,但更涉及到包含常数的精确极大极小分析。为了建立更严格的一维结果,我们引入了\emph{fugal game}松弛,其极小极大遗憾的下限开关约束OCO。我们证明了逃逸对策的最小最大遗憾至少是$ \frac{T}{\sqrt{2K}} $,从而建立了一维最优最小最大遗憾下界。为了建立与维数无关的上界,我们接下来证明了一个minimax算法提供了一个$ O(\frac{T}{\sqrt{K}}) $上界,因此得出结论,对于任何$K$,切换约束OCO的极小极大遗憾是$ Θ(\frac{T}{\sqrt{K}}) $。这是在鲜明的对比,它的离散对应,开关约束预测专家的问题,表现出一个相变之间的低开关和高开关制度的最小最大遗…