arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.04583cs.LGcs.DS
收藏

半随机噪声环境下的聚类算法

Clustering with Queries under Semi-Random Noise

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Wisconsin Institute for Discovery(威斯康星发现研究院)

Alberto Del Pia, Mingchen Ma, Christos Tzamos

摘要:

Mazumdar和Saha的开创性论文\cite{MS17a}介绍了一系列关于噪声查询聚类的工作。然而,尽管在这个问题上取得了重大进展,但所提出的方法关键取决于知道底层完全随机预言的准确错误概率。在这项工作中,我们开发了强大的学习方法,容忍一般的半随机噪声获得定性相同的保证,在完全随机模型中的最佳方法。更具体地说,给定一组具有未知底层分区的$n$点,允许我们查询点对$u,v$,以检查它们是否在同一个集群中,但是以概率$p$,可以逆向选择答案。我们表明,信息理论上$O\left(\frac{nk \log n} {(1-2p)^2}\right)$查询足以学习任何集群足够大的大小。我们的主要结果是一个计算效率高的算法,可以识别大集群与$O\left(\frac{nk \log n} {(1-2p)^2}\right) + \text{poly}\left(\log n, k, \frac{1}{1-2p} \right)$查询,匹配的保证,最知名的算法在全随机模型。作为我们的方法的一个必然结果,我们开发了第一个无参数算法的完全随机模型,回答了一个开放的问题,由\cite{MS17a}。

英文摘要:

The seminal paper by Mazumdar and Saha \cite{MS17a} introduced an extensive line of work on clustering with noisy queries. Yet, despite significant progress on the problem, the proposed methods depend crucially on knowing the exact probabilities of errors of the underlying fully-random oracle. In this work, we develop robust learning methods that tolerate general semi-random noise obtaining qualitatively the same guarantees as the best possible methods in the fully-random model. More specifically, given a set of $n$ points with an unknown underlying partition, we are allowed to query pairs of points $u,v$ to check if they are in the same cluster, but with probability $p$, the answer may be adversarially chosen. We show that information theoretically $O\left(\frac{nk \log n} {(1-2p)^2}\right)$ queries suffice to learn any cluster of sufficiently large size. Our main result is a computationally efficient algorithm that can identify large clusters with $O\left(\frac{nk \log n} {(1-2p)^2}\right) + \text{poly}\left(\log n, k, \frac{1}{1-2p} \right)$ queries, matching the guarantees of the best known algorithms in the fully-random model. As a corollary of our approach, we develop the first parameter-free algorithm for the fully-random model, answering an open question by \cite{MS17a}.

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。

↑