arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.06528cs.DS
收藏

弱超模集函数的贪婪极小化

Greedy Minimization of Weakly Supermodular Set Functions

Christos Boutsidis, Edo Liberty, Maxim Sviridenko

摘要:

定义了集函数的弱- $α$ -超模性.机器学习和数据挖掘中的许多优化目标寻求在基数约束下最小化这些函数。我们证明了这样的问题受益于一个贪婪的扩展阶段。明确地说,令$S^*$是使$f$最小化的基数$k$的最优集合,并且令$S_0$是初始解,使得$f(S_0)/f(S^*) \le ρ$。然后,大小为$|S| \le |S_0| + \lceil αk \ln(ρ/\varepsilon) \rceil$的贪婪扩展$S \supset S_0$产生$f(S)/f(S^*) \le 1+\varepsilon$。作为这个框架的示例用法,我们给出了$k$ -均值,稀疏回归和列子集选择的新双准则结果。

英文摘要:

This paper defines weak-$α$-supermodularity for set functions. Many optimization objectives in machine learning and data mining seek to minimize such functions under cardinality constrains. We prove that such problems benefit from a greedy extension phase. Explicitly, let $S^*$ be the optimal set of cardinality $k$ that minimizes $f$ and let $S_0$ be an initial solution such that $f(S_0)/f(S^*) \le ρ$. Then, a greedy extension $S \supset S_0$ of size $|S| \le |S_0| + \lceil αk \ln(ρ/\varepsilon) \rceil$ yields $f(S)/f(S^*) \le 1+\varepsilon$. As example usages of this framework we give new bicriteria results for $k$-means, sparse regression, and columns subset selection.

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。

↑