arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1408.0751cs.DS
收藏

最近邻搜索的谱方法

Spectral Approaches to Nearest Neighbor Search

Amirali Abdullah, Alexandr Andoni, Ravindran Kannan, Robert Krauthgamer

摘要:

本文研究高维最近邻搜索问题的谱算法。特别是,我们考虑一个半随机设置,其中数据集$P$在$\mathbb{R}^d$中任意地从低维$k\ll d$的未知子空间中选择,然后由完全$d$维高斯噪声扰动。我们设计的频谱NNS算法的查询时间多项式依赖于$d$和$\log n$(其中$n=|P|$)的大范围的$k$,$d$和$n$。我们的算法使用的顶部PCA向量/子空间的重复计算,并且是有效的,即使当随机噪声幅度是{ \em大得多}比$P$中的点间距离。我们的动机是,在实践中,一些谱NNS算法优于随机投影方法,否则似乎理论上最佳的最坏情况下的数据集。在本文中,我们的目的是提供这种差异的理论依据。

英文摘要:

We study spectral algorithms for the high-dimensional Nearest Neighbor Search problem (NNS). In particular, we consider a semi-random setting where a dataset $P$ in $\mathbb{R}^d$ is chosen arbitrarily from an unknown subspace of low dimension $k\ll d$, and then perturbed by fully $d$-dimensional Gaussian noise. We design spectral NNS algorithms whose query time depends polynomially on $d$ and $\log n$ (where $n=|P|$) for large ranges of $k$, $d$ and $n$. Our algorithms use a repeated computation of the top PCA vector/subspace, and are effective even when the random-noise magnitude is {\em much larger} than the interpoint distances in $P$. Our motivation is that in practice, a number of spectral NNS algorithms outperform the random-projection methods that seem otherwise theoretically optimal on worst case datasets. In this paper we aim to provide theoretical justification for this disparity.

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。

↑