arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.00248math.OCcs.LGstat.ML
收藏

基于经验域约简的紧鲁棒Optimization

Tightly Robust Optimization via Empirical Domain Reduction

NEC corporation(NEC公司);RIKEN AIP(理化学研究所)

Akihiro Yabe, Takanori Maehara

摘要:

数据驱动的决策是通过求解一个参数化的最优化问题来实现的,最优决策是通过未知真参数的最优解来给出的。我们经常需要一个满足真实约束的解决方案,即使这些约束是未知的。鲁棒优化是为了获得这样的解决方案,其中的参数的不确定性表示为一个椭球,和鲁棒性的规模由一个系数控制。在这项研究中,我们提出了一种算法来确定规模,使解决方案有一个很好的目标值,并满足真正的约束与给定的置信概率。在一定的正则性条件下,我们的算法得到的尺度是渐近的$O(1/\sqrt{n})$,而由标准方法得到的尺度是$O(\sqrt{d/n})$。这意味着我们的算法受参数维数的影响较小。

英文摘要:

Data-driven decision-making is performed by solving a parameterized optimization problem, and the optimal decision is given by an optimal solution for unknown true parameters. We often need a solution that satisfies true constraints even though these are unknown. Robust optimization is employed to obtain such a solution, where the uncertainty of the parameter is represented by an ellipsoid, and the scale of robustness is controlled by a coefficient. In this study, we propose an algorithm to determine the scale such that the solution has a good objective value and satisfies the true constraints with a given confidence probability. Under some regularity conditions, the scale obtained by our algorithm is asymptotically $O(1/\sqrt{n})$, whereas the scale obtained by a standard approach is $O(\sqrt{d/n})$. This means that our algorithm is less affected by the dimensionality of the parameters.

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。

↑