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 2006.04675cs.LGstat.ML
收藏

利用同簇重叠精确恢复被破坏的团簇

Exact Recovery of Mangled Clusters with Same-Cluster Queries

Sapienza University of Rome(罗马第一大学);Univ. of Milan(米兰大学);Google(谷歌);Istituto Italiano di Tecnologia(意大利理工学院)

Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi, Andrea Paudice

摘要:

研究了半监督主动聚类框架下的聚类恢复问题。给定一组有限的输入点,以及揭示任何两个点是否位于同一个簇中的预言,我们的目标是使用尽可能少的查询来精确地恢复所有簇。为此,我们放松了Ashtiani等人的球形$k$ -均值聚类假设。以允许具有边缘的任意椭圆形簇。这消除了聚类是基于中心的假设(即,通过优化问题定义),并且包括通过旋转、轴缩放和点删除的任何组合单独变换球形簇的所有那些情况。我们表明,即使在这个更一般的设置,它仍然是可以恢复的潜在的聚类使用的查询数量,规模仅与输入点的数量几何。更确切地说,我们设计了一个算法,给定$n$点被划分成$k$集群,使用$O(k^3 \ln k \ln n)$ oracle查询和$\tilde{O}(kn + k^3)$时间来恢复聚类,具有零误分类错误。的$O(\cdot)$符号隐藏了指数依赖的簇的维数,这是必要的,从而表征查询的复杂性的问题。我们的算法是简单的,易于实现,也可以学习集群使用低拉伸分离器,一类椭球体与额外的理论保证。在大规模人工数据集上的实验表明,该算法能够准确、高效地重构聚类。

英文摘要:

We study the cluster recovery problem in the semi-supervised active clustering framework. Given a finite set of input points, and an oracle revealing whether any two points lie in the same cluster, our goal is to recover all clusters exactly using as few queries as possible. To this end, we relax the spherical $k$-means cluster assumption of Ashtiani et al.\ to allow for arbitrary ellipsoidal clusters with margin. This removes the assumption that the clustering is center-based (i.e., defined through an optimization problem), and includes all those cases where spherical clusters are individually transformed by any combination of rotations, axis scalings, and point deletions. We show that, even in this much more general setting, it is still possible to recover the latent clustering exactly using a number of queries that scales only logarithmically with the number of input points. More precisely, we design an algorithm that, given $n$ points to be partitioned into $k$ clusters, uses $O(k^3 \ln k \ln n)$ oracle queries and $\tilde{O}(kn + k^3)$ time to recover the clustering with zero misclassification error. The $O(\cdot)$ notation hides an exponential dependence on the dimensionality of the clusters, which we show to be necessary thus characterizing the query complexity of the problem. Our algorithm is simple, easy to implement, and can also learn the clusters using low-stretch separators, a class of ellipsoids with additional theoretical guarantees. Experiments on large synthetic datasets confirm that we can reconstruct clusterings exactly and efficiently.

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。

↑