arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.07073stat.MLcs.AIcs.DScs.LG
收藏

非次模目标的鲁棒最大化

Robust Maximization of Non-Submodular Objectives

EPFL(洛桑联邦理工学院)

Ilija Bogunovic, Junyao Zhao, Volkan Cevher

摘要:

我们研究的问题,最大化的单调集函数的基数约束$k$的设置中删除一些元素$τ$从返回的集合。这项工作的重点是最坏情况下的对抗性设置。虽然当函数是子模块时存在常数因子保证,但对于非子模块目标没有保证。在这项工作中,我们提出了一个新的算法遗忘贪婪,并证明了第一个常数因子近似保证更广泛的非次模目标。所获得的理论界限是第一个常数因子界限,也保持在线性制度,即当删除$τ$的数量是线性的$k$。我们的界限依赖于已建立的参数,如子模比和一些新的,如逆曲率。我们约束这些参数的两个重要目标,包括支持选择和方差减少。最后,我们在各种数据集上证明了遗忘贪婪算法对这两个目标的鲁棒性能。

英文摘要:

We study the problem of maximizing a monotone set function subject to a cardinality constraint $k$ in the setting where some number of elements $τ$ is deleted from the returned set. The focus of this work is on the worst-case adversarial setting. While there exist constant-factor guarantees when the function is submodular, there are no guarantees for non-submodular objectives. In this work, we present a new algorithm Oblivious-Greedy and prove the first constant-factor approximation guarantees for a wider class of non-submodular objectives. The obtained theoretical bounds are the first constant-factor bounds that also hold in the linear regime, i.e. when the number of deletions $τ$ is linear in $k$. Our bounds depend on established parameters such as the submodularity ratio and some novel ones such as the inverse curvature. We bound these parameters for two important objectives including support selection and variance reduction. Finally, we numerically demonstrate the robust performance of Oblivious-Greedy for these two objectives on various datasets.

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。

↑