arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1005.1440stat.ML
收藏

Johnson-Lindenstrauss引理的改进

Improving the Johnson-Lindenstrauss Lemma

Javier Rojo, Tuan Nguyen

摘要:

Johnson-Lindenstrauss引理允许将$p-$维欧氏空间中的$n$点投影到$k-$维欧氏空间上,具有$k \ge \frac{24\ln \emph{n}}{3ε^2-2ε^3}$,使得成对距离保持在因子$1\pmε$内。在这里,工作直接与随机距离的分布,而不是诉诸矩生成函数技术,$k$的下界的改进。当与文献中发现的界限相比时,额外的维数减少至少为$13\%$,并且在某些情况下,实现高达$30\%$的额外减少。使用矩生成函数技术,我们进一步提供了一个下界$k$使用成对的$L_2$距离在空间中的点被投影和成对的$L_1$距离在空间中的投影点。与文献中得到的结果比较表明,这里提出的界限提供了一个额外的$36-40\%$减少。

英文摘要:

The Johnson-Lindenstrauss Lemma allows for the projection of $n$ points in $p-$dimensional Euclidean space onto a $k-$dimensional Euclidean space, with $k \ge \frac{24\ln \emph{n}}{3ε^2-2ε^3}$, so that the pairwise distances are preserved within a factor of $1\pmε$. Here, working directly with the distributions of the random distances rather than resorting to the moment generating function technique, an improvement on the lower bound for $k$ is obtained. The additional reduction in dimension when compared to bounds found in the literature, is at least $13\%$, and, in some cases, up to $30\%$ additional reduction is achieved. Using the moment generating function technique, we further provide a lower bound for $k$ using pairwise $L_2$ distances in the space of points to be projected and pairwise $L_1$ distances in the space of the projected points. Comparison with the results obtained in the literature shows that the bound presented here provides an additional $36-40\%$ reduction.

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。

↑