arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/9901004cs.IRcs.CGcs.DBcs.DS
收藏

相似搜索的几何学:维数灾难与测度集中

On the geometry of similarity search: dimensionality curse and concentration of measure

Vladimir Pestov

摘要:

我们认为,在大数据集的相似性为基础的搜索影响的维数灾难是一种表现的现象的浓度的措施对高维结构。我们证明,在某些几何假设下的查询域$Ω$和数据集$X$,如果$Ω$满足所谓的浓度属性,那么对于大多数查询点$x^\ast$的球半径$(1+\e)d_X(x^\ast)$集中在$x^\ast$包含所有点的$X$或至少$C_1\exp(-C_2\e^2n)$的。这里,$d_X(x^\ast)$是从$x^\ast$到$X$中最近邻的距离,$n$是$Ω$的维数。

英文摘要:

We suggest that the curse of dimensionality affecting the similarity-based search in large datasets is a manifestation of the phenomenon of concentration of measure on high-dimensional structures. We prove that, under certain geometric assumptions on the query domain $Ω$ and the dataset $X$, if $Ω$ satisfies the so-called concentration property, then for most query points $x^\ast$ the ball of radius $(1+\e)d_X(x^\ast)$ centred at $x^\ast$ contains either all points of $X$ or else at least $C_1\exp(-C_2\e^2n)$ of them. Here $d_X(x^\ast)$ is the distance from $x^\ast$ to the nearest neighbour in $X$ and $n$ is the dimension of $Ω$.

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。

↑