arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.00029cs.LGmath.PRstat.ML
收藏

具有最佳精度的随机嵌入

Random Embeddings with Optimal Accuracy

University of Luxembourg(卢森堡大学)

Maciej Skorski

摘要:

这项工作构造的Jonson-Lindenstrauss嵌入最好的精度,测量方差,均方误差和指数浓度的长度失真。任何数据和嵌入维度的下限都是确定的,并伴随着匹配和有效的采样结构(建立在正交矩阵上)。新的技术:一个单位球参数化,使用奇异值潜变量和舒尔凸性是独立的利益。

英文摘要:

This work constructs Jonson-Lindenstrauss embeddings with best accuracy, as measured by variance, mean-squared error and exponential concentration of the length distortion. Lower bounds for any data and embedding dimensions are determined, and accompanied by matching and efficiently samplable constructions (built on orthogonal matrices). Novel techniques: a unit sphere parametrization, the use of singular-value latent variables and Schur-convexity are of independent interest.

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。

↑