arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2408.04620cs.DS
收藏

正则化无约束弱子模最大化

Regularized Unconstrained Weakly Submodular Maximization

Yanhui Zhu, Samik Basu, A. Pavan

AI总结:

本文针对单调非负弱子模函数与模函数差值的最大化问题,提出一种低预言机调用次数的确定性近似算法,理论近似比更优且支持近似预言机,经真实场景实验验证可高效生成高质量解。

摘要:

子模优化在机器学习与数据挖掘领域有诸多应用。本文研究形如$h = f-c$的函数最大化问题,其中$f$是单调非负弱子模集合函数,$c$是模函数。我们设计了一种确定性近似算法,该算法对函数$h$的预言机调用次数为${O}(\frac{n}ε\frac{n}{γε})$,输出集合${S}$满足$h({S}) \geq γ(1-ε)f(OPT)-c(OPT)-\frac{c(OPT)}{γ(1-ε)}\log\frac{f(OPT)}{c(OPT)}$,其中$γ$为$f$的子模率。现有针对该问题的算法要么近似比更差,要么运行时间为二次方级。我们还给出了算法在$f$为近似预言机情况下的近似比。我们通过在真实应用场景中开展大量实证评估验证了理论结果,包括针对子模效用函数$f$的顶点覆盖和影响扩散问题,以及针对弱子模$f$的贝叶斯A最优设计问题。实验结果表明,我们的算法能高效生成高质量解。

英文摘要:

Submodular optimization finds applications in machine learning and data mining. In this paper, we study the problem of maximizing functions of the form $h = f-c$, where $f$ is a monotone, non-negative, weakly submodular set function and $c$ is a modular function. We design a deterministic approximation algorithm that runs with ${O}(\frac{n}ε\log \frac{n}{γε})$ oracle calls to function $h$, and outputs a set ${S}$ such that $h({S}) \geq γ(1-ε)f(OPT)-c(OPT)-\frac{c(OPT)}{γ(1-ε)}\log\frac{f(OPT)}{c(OPT)}$, where $γ$ is the submodularity ratio of $f$. Existing algorithms for this problem either admit a worse approximation ratio or have quadratic runtime. We also present an approximation ratio of our algorithm for this problem with an approximate oracle of $f$. We validate our theoretical results through extensive empirical evaluations on real-world applications, including vertex cover and influence diffusion problems for submodular utility function $f$, and Bayesian A-Optimal design for weakly submodular $f$. Our experimental results demonstrate that our algorithms efficiently achieve high-quality solutions.

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。

↑