arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.05064cs.LGstat.ML
收藏

基于理论的最近邻模型评价方法的应用

A Theory-Based Evaluation of Nearest Neighbor Models Put Into Practice

TU Dortmund(多特蒙德工业大学)

Hendrik Fichtenberger, Dennis Rohde

摘要:

在$k$ -最近邻模型($k$ -NN)中,我们给出一组点$P$,并且我们将通过根据某种度量返回$P$中$q$的$k$最近邻来回答查询$q$。这一概念在数据分析和数据处理的许多领域都是至关重要的,例如,计算机视觉、文档检索和机器学习。许多$k$ -NN算法已被公布和实施,但往往是参数和计算的$k$ -NN的精度之间的关系是不明确的。我们从理论上研究了$k$ -NN图的性质检验,并从经验上进行了评价:给定一个点集$P \subset \mathbb{R}^δ$和一个有向图$G=(P,E)$,$G$是否是一个$k$ -NN图,即,每个点$p \in P$都有到它的$k$最近邻居的向外边,或者它是$ε$ -远不是$k$ -NN图?这里,$ε$ -远意味着为了使$G$成为$k$ -NN图,必须改变多于$ε$ -分数的边。我们开发了一个随机算法,单侧误差决定了这个问题,即,$k$属性的属性测试器,其复杂性根据其检查的顶点和边的数量来衡量$O(\sqrt{n} k^2 / ε^2)$,并且我们证明了$Ω(\sqrt{n / εk})$的下界。我们评估我们的测试经验上的$k$ -NN模型计算的各种算法,并表明,它可以用来检测$k$ -NN模型的准确性差,在显着更少的时间比$k$ -NN模型的建设时间。

英文摘要:

In the $k$-nearest neighborhood model ($k$-NN), we are given a set of points $P$, and we shall answer queries $q$ by returning the $k$ nearest neighbors of $q$ in $P$ according to some metric. This concept is crucial in many areas of data analysis and data processing, e.g., computer vision, document retrieval and machine learning. Many $k$-NN algorithms have been published and implemented, but often the relation between parameters and accuracy of the computed $k$-NN is not explicit. We study property testing of $k$-NN graphs in theory and evaluate it empirically: given a point set $P \subset \mathbb{R}^δ$ and a directed graph $G=(P,E)$, is $G$ a $k$-NN graph, i.e., every point $p \in P$ has outgoing edges to its $k$ nearest neighbors, or is it $ε$-far from being a $k$-NN graph? Here, $ε$-far means that one has to change more than an $ε$-fraction of the edges in order to make $G$ a $k$-NN graph. We develop a randomized algorithm with one-sided error that decides this question, i.e., a property tester for the $k$-NN property, with complexity $O(\sqrt{n} k^2 / ε^2)$ measured in terms of the number of vertices and edges it inspects, and we prove a lower bound of $Ω(\sqrt{n / εk})$. We evaluate our tester empirically on the $k$-NN models computed by various algorithms and show that it can be used to detect $k$-NN models with bad accuracy in significantly less time than the building time of the $k$-NN model.

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。

↑