arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1011.6397cs.DScs.CCmath.PR
收藏

几乎最优显式Johnson-Lindenstrauss变换

Almost Optimal Explicit Johnson-Lindenstrauss Transformations

Raghu Meka

摘要:

约翰森-林登施特劳斯引理是概率论中的一个基本结果,在高维几何中的算法设计和分析中有许多应用。满足Johnson-Lindenstrauss性质的线性嵌入的大多数已知构造都涉及随机性。我们解决了显式构造这种嵌入族的问题,并提供了一种几乎最佳使用随机性的构造:我们使用O(log(n/delta)log(log(n/delta)/ε))随机位将n维嵌入到O(log(1/delta)/ε ^2)维,错误概率最多为delta,失真最多为ε。特别地,对于delta = 1/poly(n)和固定的k,我们使用O(log n loglog n)随机位。以前的构造至少需要O(log^2 n)个随机位才能得到多项式小误差。

英文摘要:

The Johnson-Lindenstrauss lemma is a fundamental result in probability with several applications in the design and analysis of algorithms in high dimensional geometry. Most known constructions of linear embeddings that satisfy the Johnson-Lindenstrauss property involve randomness. We address the question of explicitly constructing such embedding families and provide a construction with an almost optimal use of randomness: we use O(log(n/delta)log(log(n/delta)/epsilon)) random bits for embedding n dimensions to O(log(1/delta)/epsilon^2) dimensions with error probability at most delta, and distortion at most epsilon. In particular, for delta = 1/poly(n) and fixed epsilon, we use O(log n loglog n) random bits. Previous constructions required at least O(log^2 n) random bits to get polynomially small error.

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。

↑