k-means++:只需几步即可获得常数近似值
k-means++: few more steps yield constant approximation
摘要:
Arthur和Vassilvitskii的k-means++算法(SODA 2007)是解决k-means聚类问题的最先进算法,并且已知在期望中给出O(log k)近似。最近,Lattanzi和Sohler(ICML 2019)提出了用O(k log log k)局部搜索步骤来增强k-means++,以产生对k-means聚类问题的恒定近似(预期)。在本文中,我们改进了他们的分析表明,对于任何任意小的常数$\eps > 0$,只有$\eps k$额外的本地搜索步骤,可以实现一个常数近似保证(在k中具有高概率),解决了一个公开的问题,在他们的论文。
英文摘要:
The k-means++ algorithm of Arthur and Vassilvitskii (SODA 2007) is a state-of-the-art algorithm for solving the k-means clustering problem and is known to give an O(log k)-approximation in expectation. Recently, Lattanzi and Sohler (ICML 2019) proposed augmenting k-means++ with O(k log log k) local search steps to yield a constant approximation (in expectation) to the k-means clustering problem. In this paper, we improve their analysis to show that, for any arbitrarily small constant $\eps > 0$, with only $\eps k$ additional local search steps, one can achieve a constant approximation guarantee (with high probability in k), resolving an open problem in their paper.
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。