arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1512.04433cs.LGcs.DSmath.FA
收藏

任意集的二元嵌入的近最优界

Near-Optimal Bounds for Binary Embeddings of Arbitrary Sets

Simons Institute(西蒙斯研究所);UC Berkeley(加州大学伯克利分校)

Samet Oymak, Ben Recht

摘要:

研究了单位球面的子集$K$嵌入到汉明立方体$\{-1,+1\}^m$中的问题。我们的特点失真和样本的复杂性$m$之间的权衡的高斯宽度$ω(K)$的集合。对于子空间和几个结构集,我们表明,高斯映射提供了最佳的权衡$m\sim δ^{-2}ω^2(K)$,特别是$δ$失真需要$m\approxδ^{-2}{d}$,其中$d$是子空间的维度。对于一般的集合,我们提供了清晰的特征,简化后减少到$m\approx{δ^{-4}}{ω^2(K)}$。我们提供了改进的结果,在彼此非常接近的地方嵌入的点,这是相关的局部敏感散列。我们还讨论了更快的二进制嵌入,其中一个利用快速约翰逊-林登施陶斯变换的基础上的初始草图过程。最后,我们列出几个数值观测和讨论开放的问题。

英文摘要:

We study embedding a subset $K$ of the unit sphere to the Hamming cube $\{-1,+1\}^m$. We characterize the tradeoff between distortion and sample complexity $m$ in terms of the Gaussian width $ω(K)$ of the set. For subspaces and several structured sets we show that Gaussian maps provide the optimal tradeoff $m\sim δ^{-2}ω^2(K)$, in particular for $δ$ distortion one needs $m\approxδ^{-2}{d}$ where $d$ is the subspace dimension. For general sets, we provide sharp characterizations which reduces to $m\approx{δ^{-4}}{ω^2(K)}$ after simplification. We provide improved results for local embedding of points that are in close proximity of each other which is related to locality sensitive hashing. We also discuss faster binary embedding where one takes advantage of an initial sketching procedure based on Fast Johnson-Lindenstauss Transform. Finally, we list several numerical observations and discuss open problems.

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。

↑