arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05583cs.LGcs.CEstat.ML
收藏

次模最大覆盖问题的变分优化

Variational Optimization for the Submodular Maximum Coverage Problem

Ant Financial(蚂蚁金融)

Jian Du, Zhigang Hua, Shuang Yang

摘要:

我们研究的\emph{submodular maximum coverage problem}(SMCP),这是涉及到广泛的应用。我们提供了这个问题的第一变分近似的基础上Nemhauser分歧,并表明它可以有效地解决变分优化。该算法在两个步骤之间交替:(1)E步骤,其估计变分参数以使参数化的\emph{modular}下限最大化;以及(2)M步骤,其通过求解局部近似问题来更新解。我们提供了理论分析的性能所提出的方法和它的曲率依赖的近似因子,并在一些公共数据集和几个应用任务的经验评估。

英文摘要:

We examine the \emph{submodular maximum coverage problem} (SMCP), which is related to a wide range of applications. We provide the first variational approximation for this problem based on the Nemhauser divergence, and show that it can be solved efficiently using variational optimization. The algorithm alternates between two steps: (1) an E step that estimates a variational parameter to maximize a parameterized \emph{modular} lower bound; and (2) an M step that updates the solution by solving the local approximate problem. We provide theoretical analysis on the performance of the proposed approach and its curvature-dependent approximate factor, and empirically evaluate it on a number of public data sets and several application tasks.

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。

↑