arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.05232cs.DS
收藏

关于k-Means/Median Cost函数

On the k-Means/Median Cost Function

Anup Bhattacharya, Yoav Freund, Ragesh Jaiswal

摘要:

在这项工作中,我们研究了$k$ -平均成本函数。给定一个数据集$X \subseteq \mathbb{R}^d$和一个整数$k$,欧几里德$k$ -均值问题的目标是找到一组$k$中心$C \subseteq \mathbb{R}^d$,使得$Φ(C, X) \equiv \sum_{x \in X} \min_{c \in C} ||x - c||^2$最小化.令$Δ(X,k) \equiv \min_{C \subseteq \mathbb{R}^d} Φ(C, X)$表示最优$k$均值解的成本。对于任何数据集$X$,$Δ(X,k)$随着$k$的增加而减少。在这项工作中,我们试图更准确地理解这种行为。对于任何数据集$X \subseteq \mathbb{R}^d$、整数$k \geq 1$和精度参数$\varepsilon > 0$,令$L(X, k, \varepsilon)$表示使得$Δ(X, L(X, k, \varepsilon)) \leq \varepsilon \cdot Δ(X,k)$的最小整数。我们给出了这个量的上界和下界。我们的技术推广的度量$k$ -中位数问题在任意度量空间,我们给出的两倍的度量维度的界限。最后,我们观察到,对于任何数据集$X$,我们可以使用$D^2$ -采样来计算大小为$O \left(L(X, k, \varepsilon/c) \right)$的集合$S$,使得对于某个固定常数$c$,$Φ(S,X) \leq \varepsilon \cdot Δ(X,k)$。我们还讨论了我们的边界的一些应用。

英文摘要:

In this work, we study the $k$-means cost function. Given a dataset $X \subseteq \mathbb{R}^d$ and an integer $k$, the goal of the Euclidean $k$-means problem is to find a set of $k$ centers $C \subseteq \mathbb{R}^d$ such that $Φ(C, X) \equiv \sum_{x \in X} \min_{c \in C} ||x - c||^2$ is minimized. Let $Δ(X,k) \equiv \min_{C \subseteq \mathbb{R}^d} Φ(C, X)$ denote the cost of the optimal $k$-means solution. For any dataset $X$, $Δ(X,k)$ decreases as $k$ increases. In this work, we try to understand this behaviour more precisely. For any dataset $X \subseteq \mathbb{R}^d$, integer $k \geq 1$, and a precision parameter $\varepsilon > 0$, let $L(X, k, \varepsilon)$ denote the smallest integer such that $Δ(X, L(X, k, \varepsilon)) \leq \varepsilon \cdot Δ(X,k)$. We show upper and lower bounds on this quantity. Our techniques generalize for the metric $k$-median problem in arbitrary metric spaces and we give bounds in terms of the doubling dimension of the metric. Finally, we observe that for any dataset $X$, we can compute a set $S$ of size $O \left(L(X, k, \varepsilon/c) \right)$ using $D^2$-sampling such that $Φ(S,X) \leq \varepsilon \cdot Δ(X,k)$ for some fixed constant $c$. We also discuss some applications of our bounds.

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。

↑