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 2202.09784cs.LGcs.AIcs.CVstat.ME
收藏

基于极值理论的概率分布聚类

Clustering by the Probability Distributions from Extreme Value Theory

Fudan University(复旦大学);Zhejiang Normal University(浙江师范大学)

Sixiao Zheng, Ke Fan, Yanxi Hou, Jianfeng Feng, Yanwei Fu

摘要:

聚类是无监督学习的一项重要任务。它试图自动将实例分离成连贯的子集。k-means算法是一种著名的聚类算法,它将边界上的样本点分配到一个唯一的类中,但没有利用样本的分布或密度信息。相比之下,考虑每个样本在可能的聚类中的概率可能更有益。为此,本文推广了k-means来模拟聚类的分布。因此,我们的新的聚类算法模型的分布的距离超过阈值的广义帕累托分布(GPD)极值理论(EVT)的质心。值得注意的是,我们提出了质心边缘距离的概念,使用GPD建立一个概率模型,每个类,并执行聚类算法的基础上的覆盖概率函数从GPD。这样的GPD k均值因此使得能够从概率的角度进行聚类算法。相应地,我们还引入了一个朴素的基线,称为广义极值(GEV)k均值。GEV拟合块最大值的分布。相比之下,GPD拟合超过足够大的阈值的到质心的距离的分布,导致GPD k均值的更稳定的性能。值得注意的是,GEV k-means还可以估计聚类结构,因此比经典的k-means表现得相当好。因此,在合成数据集和真实数据集上的广泛实验表明,GPD k-means优于竞争对手。github代码在https://github.com/sixiaozheng/EVT-K-means上发布。

英文摘要:

Clustering is an essential task to unsupervised learning. It tries to automatically separate instances into coherent subsets. As one of the most well-known clustering algorithms, k-means assigns sample points at the boundary to a unique cluster, while it does not utilize the information of sample distribution or density. Comparably, it would potentially be more beneficial to consider the probability of each sample in a possible cluster. To this end, this paper generalizes k-means to model the distribution of clusters. Our novel clustering algorithm thus models the distributions of distances to centroids over a threshold by Generalized Pareto Distribution (GPD) in Extreme Value Theory (EVT). Notably, we propose the concept of centroid margin distance, use GPD to establish a probability model for each cluster, and perform a clustering algorithm based on the covering probability function derived from GPD. Such a GPD k-means thus enables the clustering algorithm from the probabilistic perspective. Correspondingly, we also introduce a naive baseline, dubbed as Generalized Extreme Value (GEV) k-means. GEV fits the distribution of the block maxima. In contrast, the GPD fits the distribution of distance to the centroid exceeding a sufficiently large threshold, leading to a more stable performance of GPD k-means. Notably, GEV k-means can also estimate cluster structure and thus perform reasonably well over classical k-means. Thus, extensive experiments on synthetic datasets and real datasets demonstrate that GPD k-means outperforms competitors. The github codes are released in https://github.com/sixiaozheng/EVT-K-means.

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。

↑