arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01006cs.DScs.LGcs.NAmath.NAmath.PR
收藏

噪声向量的Johnson-Lindenstrauss嵌入--利用噪声

Johnson-Lindenstrauss embeddings for noisy vectors -- taking advantage of the noise

Zhen Shao

摘要:

本文研究了亚采样和散列作为工具的近似欧氏范数保持嵌入(未知)加性高斯噪声的向量的理论性质。这种嵌入有时被称为约翰逊-林登施特劳斯嵌入,因为它们的著名引理。以前的工作表明,作为稀疏嵌入,子采样和哈希的成功密切依赖于要映射的向量的$l_\infty$与$l_2$的比率。本文表明,噪声的存在消除了这种约束,在高维,换句话说,稀疏嵌入,如子采样和散列具有可比的嵌入维数密集嵌入有类似的近似范数保持降维属性。关键是,噪声应该被视为一种待开发的信息,而不仅仅是要去除的东西。理论界的子采样和散列恢复的近似范数的高维向量在噪声的存在下,推导出,与数值例子显示更好的性能,在噪声的存在下实现。

英文摘要:

This paper investigates theoretical properties of subsampling and hashing as tools for approximate Euclidean norm-preserving embeddings for vectors with (unknown) additive Gaussian noises. Such embeddings are sometimes called Johnson-lindenstrauss embeddings due to their celebrated lemma. Previous work shows that as sparse embeddings, the success of subsampling and hashing closely depends on the $l_\infty$ to $l_2$ ratios of the vector to be mapped. This paper shows that the presence of noise removes such constrain in high-dimensions, in other words, sparse embeddings such as subsampling and hashing with comparable embedding dimensions to dense embeddings have similar approximate norm-preserving dimensionality-reduction properties. The key is that the noise should be treated as an information to be exploited, not simply something to be removed. Theoretical bounds for subsampling and hashing to recover the approximate norm of a high dimension vector in the presence of noise are derived, with numerical illustrations showing better performances are achieved in the presence of noise.

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。

↑