arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0812.0146cs.DS
收藏

度量树索引方案在高维精确相似搜索中的性能下限

Lower Bounds on Performance of Metric Tree Indexing Schemes for Exact Similarity Search in High Dimensions

Vladimir Pestov

摘要:

在一个严格的数学模型,我们分析了灾难的维数确定性的精确相似性搜索的背景下流行的索引方案:度量树。数据集$X$从域$Ω$随机采样,该域配备有距离$ρ$和基础概率分布$μ$。在执行渐近分析时,我们将$Ω$的内在维度$d$发送到无穷大,并假设数据集$n$的大小在$d$中以超多项式但次指数的方式增长。精确相似性搜索是指在数据集$X$中找到查询点$ω\inΩ$的最近邻居,其中查询点与数据点服从相同的概率分布$μ$。令$\mathscr F$表示$Ω$上的所有1-Lipschitz函数的类,其可用作构造分层度量树索引方案中的决策函数。设所有集合的类$\{ω\colon f(ω)\geq a\}$,$a\in\R$的VC维数为$o(n^{1/4}/\log^2n)$ . (In从Goldberg和Jerrum 1995年的结果来看,甚至更强的复杂性假设$d^{O(1)}$也是合理的。)我们推导出$(Ω,X)$中基于层次度量树的精确相似性搜索索引方案的预期平均情况性能的$Ω(n^{1/4})$下界。特别地,这个界限在$d$中是超多项式的。

英文摘要:

Within a mathematically rigorous model, we analyse the curse of dimensionality for deterministic exact similarity search in the context of popular indexing schemes: metric trees. The datasets $X$ are sampled randomly from a domain $Ω$, equipped with a distance, $ρ$, and an underlying probability distribution, $μ$. While performing an asymptotic analysis, we send the intrinsic dimension $d$ of $Ω$ to infinity, and assume that the size of a dataset, $n$, grows superpolynomially yet subexponentially in $d$. Exact similarity search refers to finding the nearest neighbour in the dataset $X$ to a query point $ω\inΩ$, where the query points are subject to the same probability distribution $μ$ as datapoints. Let $\mathscr F$ denote a class of all 1-Lipschitz functions on $Ω$ that can be used as decision functions in constructing a hierarchical metric tree indexing scheme. Suppose the VC dimension of the class of all sets $\{ω\colon f(ω)\geq a\}$, $a\in\R$ is $o(n^{1/4}/\log^2n)$. (In view of a 1995 result of Goldberg and Jerrum, even a stronger complexity assumption $d^{O(1)}$ is reasonable.) We deduce the $Ω(n^{1/4})$ lower bound on the expected average case performance of hierarchical metric-tree based indexing schemes for exact similarity search in $(Ω,X)$. In paricular, this bound is superpolynomial in $d$.

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。

↑