arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1106.1379cs.LG
收藏

一个统一的数据近似和聚类框架

A Unified Framework for Approximating and Clustering Data

California Institute of Technology(加州理工学院);Open University of Israel(以色列开放大学)

Dan Feldman, Michael Langberg

摘要:

给定一个基集$X$上的$n$正函数的集合$F$,我们考虑在$x\in X$上最小化表达式$\sum_{f\in F}f(x)$的$x^*$的计算问题.一个典型的应用是\emph{shape fitting},其中我们希望通过来自(可能是无限的)形状族$X$的形状$x$来近似$n$元素(例如点)的集合$P$。这里,每个点$p\in P$对应于函数$f$,使得$f(x)$是从$p$到$x$的距离,并且我们寻求使$P$中的每个点的距离之和最小化的形状$x$。在$k$聚类变体中,每个$x\in X$是$k$形状的元组,而$f(x)$是从$p$到其在$x$中最接近的形状的距离.我们的主要结果是一个统一的框架,用于构建{ \em coresets}和{ \em近似聚类},这样的一般功能集。为了实现我们的结果,我们锻造之间的联系,从PAC学习和VC维理论的经典和定义良好的概念$\varepsilon$ -近似,相对较新的(不那么一致)范式的coresets,这是某种“压缩表示”的输入集$F$。使用传统的技术,coreset通常意味着相应的优化问题的LTAS(线性时间近似方案),它可以并行计算,通过一次通过数据,并且只使用多对数空间(即,在流模型中)。我们将展示如何推广我们的框架的平方距离(如在$k$ -平均),距离$q$次幂,和确定性的结构的结果。

英文摘要:

Given a set $F$ of $n$ positive functions over a ground set $X$, we consider the problem of computing $x^*$ that minimizes the expression $\sum_{f\in F}f(x)$, over $x\in X$. A typical application is \emph{shape fitting}, where we wish to approximate a set $P$ of $n$ elements (say, points) by a shape $x$ from a (possibly infinite) family $X$ of shapes. Here, each point $p\in P$ corresponds to a function $f$ such that $f(x)$ is the distance from $p$ to $x$, and we seek a shape $x$ that minimizes the sum of distances from each point in $P$. In the $k$-clustering variant, each $x\in X$ is a tuple of $k$ shapes, and $f(x)$ is the distance from $p$ to its closest shape in $x$. Our main result is a unified framework for constructing {\em coresets} and {\em approximate clustering} for such general sets of functions. To achieve our results, we forge a link between the classic and well defined notion of $\varepsilon$-approximations from the theory of PAC Learning and VC dimension, to the relatively new (and not so consistent) paradigm of coresets, which are some kind of "compressed representation" of the input set $F$. Using traditional techniques, a coreset usually implies an LTAS (linear time approximation scheme) for the corresponding optimization problem, which can be computed in parallel, via one pass over the data, and using only polylogarithmic space (i.e, in the streaming model). We show how to generalize the results of our framework for squared distances (as in $k$-mean), distances to the $q$th power, and deterministic constructions.

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。

↑