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 2307.09616cs.DSmath.OC
收藏

具有向下闭合凸约束的连续非单调 DR-次模最大化

Continuous Non-monotone DR-submodular Maximization with Down-closed Convex Constraint

Shengminjie Chen, Donglei Du, Wenguo Yang, Dachuan Xu, Suixiang Gao

AI总结:

研究了受向下闭合凸约束的连续非单调DR-次模最大化问题,通过构建实例揭示驻点近似比差的缺陷,并将两种离散算法扩展至连续域以获得更优的近似比。

摘要:

我们研究了受向下闭合凸可解约束的连续非单调 DR-次模最大化问题。我们的第一个贡献是构建了一个例子来证明(一阶)驻点可能具有任意糟糕的近似比,并且它们通常位于可行域的边界上。这些发现与单调情况形成对比,在单调情况下,任何驻点都能产生 1/2 的近似比(Hassani 等人 (2017))。此外,该例子提供了关于如何通过避免糟糕的驻点来设计改进算法的见解,例如受限连续局部搜索算法(Chekuri 等人 (2014))和辅助测量连续贪心算法(Buchbinder 和 Feldman (2019))。然而,后两种算法的分析仅适用于离散域,因为两者都需要调用不等式,即任何次模集合函数的多线性扩展的下界为其 Lovasz 扩展。因此,我们的第二个贡献是消除这一限制,并证明这两种算法都可以扩展到连续域,同时保持相同的近似比,从而为同一问题提供优于 Bian 等人 (2017a) 的改进近似比。最后,我们还进行了数值实验,以在机器学习和人工智能中出现的问题上演示我们的算法。

英文摘要:

We investigate the continuous non-monotone DR-submodular maximization problem subject to a down-closed convex solvable constraint. Our first contribution is to construct an example to demonstrate that (first-order) stationary points can have arbitrarily bad approximation ratios, and they are usually on the boundary of the feasible domain. These findings are in contrast with the monotone case where any stationary point yields a $1/2$-approximation (Hassani et al. (2017)). Moreover, this example offers insights on how to design improved algorithms by avoiding bad stationary points, such as the restricted continuous local search algorithm (Chekuri et al. (2014)) and the aided measured continuous greedy (Buchbinder and Feldman (2019)). However, the analyses in the last two algorithms only work for the discrete domain because both need to invoke the inequality that the multilinear extension of any submodular set function is bounded from below by its Lovasz extension. Our second contribution, therefore, is to remove this restriction and show that both algorithms can be extended to the continuous domain while retaining the same approximation ratios, and hence offering improved approximation ratios over those in Bian et al. (2017a). for the same problem. At last, we also include numerical experiments to demonstrate our algorithms on problems arising from machine learning and artificial intelligence.

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。

↑