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 1812.07075cs.DS
收藏

信息理论聚类很难近似

Information theoretical clustering is hard to approximate

Ferdinando Cicalese, Eduardo Laber

摘要:

杂质度量$I: \mathbb{R}^d \mapsto \mathbb{R}^+$是将$d$维向量${\bf v}$分配给非负值$I({\bf v})$的函数,使得相对于其坐标值的${\bf v}$越均匀,其杂质越大。一个众所周知的杂质度量的例子是熵杂质。研究了基于不纯测度的聚类问题。令$V$是$n$的集合,该集合包括许多具有非负分量的$d$维向量。给定$V$和杂质量度$I$,目标是找到将$V$划分为$k$基团$V_1,\ldots,V_k$的分区${\mathcal P}$,以便使${\cal P}$中基团的杂质总和最小化,即,$I({\cal P})= \sum_{i=1}^{k} I\bigg(\sum_{ {\bf v} \in V_i} {\bf v} \bigg).$杂质最小化已被广泛用作概率分布聚类(KL-发散)以及分类聚类中的质量评估指标。然而,在基于度量的聚类的情况下,目前的知识的近似性和不可近似性的结果是非常有限的杂质措施为基础的聚类。在这里,我们有助于改变这种情况下,证明了熵杂质措施的问题不承认PTAS,即使所有的向量有相同的$\ell_1$规范。这一结果解决了一个问题,仍然是开放的,在以前的工作就这一主题[Chaudhuri和麦格雷戈COLT 08;阿克曼等。11]。

英文摘要:

An impurity measures $I: \mathbb{R}^d \mapsto \mathbb{R}^+$ is a function that assigns a $d$-dimensional vector ${\bf v}$ to a non-negative value $I({\bf v})$ so that the more homogeneous ${\bf v}$, with respect to the values of its coordinates, the larger its impurity. A well known example of impurity measures is the Entropy impurity. We study the problem of clustering based on impurity measures. Let $V$ be a collection of $n$ many $d$-dimensional vectors with non-negative components. Given $V$ and an impurity measure $I$, the goal is to find a partition ${\mathcal P}$ of $V$ into $k$ groups $V_1,\ldots,V_k$ so as to minimize the sum of the impurities of the groups in ${\cal P}$, i.e., $I({\cal P})= \sum_{i=1}^{k} I\bigg(\sum_{ {\bf v} \in V_i} {\bf v} \bigg).$ Impurity minimization has been widely used as quality assessment measure in probability distribution clustering (KL-divergence) as well as in categorical clustering. However, in contrast to the case of metric based clustering, the current knowledge of impurity measure based clustering in terms of approximation and inapproximability results is very limited. Here, we contribute to change this scenario by proving that for the Entropy impurity measure the problem does not admit a PTAS even when all vectors have the same $\ell_1$ norm. This result solves a question that remained open in previous work on this topic [Chaudhuri and McGregor COLT 08; Ackermann et. al. ECCC 11].

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。

↑