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 1502.05746cs.DScs.ITmath.IT
收藏

二进制嵌入:基本极限与快速算法

Binary Embedding: Fundamental Limits and Fast Algorithm

Xinyang Yi, Constantine Caramanis, Eric Price

摘要:

二进制嵌入是一种非线性降维方法,其中高维数据嵌入到汉明立方体中,同时保持原始空间的结构。具体来说,对于任意的$N$不同的点在$\mathbb{S}^{p-1}$,我们的目标是编码每个点使用$m$维二进制字符串,这样我们就可以重建他们的测地线距离高达$δ$均匀失真。现有的二进制嵌入算法要么缺乏理论保证,要么受到运行时间$O\big(mp\big)$的影响。我们做出三个贡献:(1)我们建立了一个下界,表明任何二进制嵌入不经意的点集需要$m = Ω(\frac{1}{δ^2}\log{N})$位和一个类似的下界为非不经意嵌入到汉明距离;(2)[删除,见评论];(3)我们还提供了一个分析结果,关于嵌入一个一般的点集$K \subseteq \mathbb{S}^{p-1}$甚至无限大。我们的理论研究结果支持通过实验合成和真实的数据集。

英文摘要:

Binary embedding is a nonlinear dimension reduction methodology where high dimensional data are embedded into the Hamming cube while preserving the structure of the original space. Specifically, for an arbitrary $N$ distinct points in $\mathbb{S}^{p-1}$, our goal is to encode each point using $m$-dimensional binary strings such that we can reconstruct their geodesic distance up to $δ$ uniform distortion. Existing binary embedding algorithms either lack theoretical guarantees or suffer from running time $O\big(mp\big)$. We make three contributions: (1) we establish a lower bound that shows any binary embedding oblivious to the set of points requires $m = Ω(\frac{1}{δ^2}\log{N})$ bits and a similar lower bound for non-oblivious embeddings into Hamming distance; (2) [DELETED, see comment]; (3) we also provide an analytic result about embedding a general set of points $K \subseteq \mathbb{S}^{p-1}$ with even infinite size. Our theoretical findings are supported through experiments on both synthetic and real data sets.

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。

↑