arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.08423cs.DScs.CGcs.LG
收藏

稳定聚类图的局部结构

On the Local Structure of Stable Clustering Instances

University of Copenhagen(哥本哈根大学);Sapienza University of Rome(罗马大学)

Vincent Cohen-Addad, Chris Schwiegelshohn

摘要:

我们研究了经典的$k$ -中位数和$k$ -均值聚类目标在超越最坏情况的情况下。我们考虑了三个旨在表征真实世界输入的结构化数据的概念:分布稳定性(由Awasthi,Blum和Sheffet介绍,FOCS 2010),谱可分性(由Kumar和Kannan介绍,FOCS 2010),扰动弹性(由Bilu和Linial介绍,ICS 2010)。我们证明结构的结果表明,满足至少一个条件的输入是固有的“本地”。也就是说,对于任何这样的输入,任何局部最优解在结构和目标值方面都接近全局最优解。作为一个推论,我们得到广泛使用的本地搜索算法具有很强的性能保证的任务,恢复底层的最佳聚类,并获得一个集群的小成本。这是理解集群应用程序中本地搜索策略成功的重要一步。

英文摘要:

We study the classic $k$-median and $k$-means clustering objectives in the beyond-worst-case scenario. We consider three well-studied notions of structured data that aim at characterizing real-world inputs: Distribution Stability (introduced by Awasthi, Blum, and Sheffet, FOCS 2010), Spectral Separability (introduced by Kumar and Kannan, FOCS 2010), Perturbation Resilience (introduced by Bilu and Linial, ICS 2010). We prove structural results showing that inputs satisfying at least one of the conditions are inherently "local". Namely, for any such input, any local optimum is close both in term of structure and in term of objective value to the global optima. As a corollary we obtain that the widely-used Local Search algorithm has strong performance guarantees for both the tasks of recovering the underlying optimal clustering and obtaining a clustering of small cost. This is a significant step toward understanding the success of local search heuristics in clustering applications.

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。

↑