arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.02574cs.CGcs.LG
收藏

基于生成点集的稀疏逼近

Sparse Approximation via Generating Point Sets

Carnegie Mellon University(卡内基梅隆大学);University of Illinois(伊利诺伊大学);University of Texas at Dallas(德克萨斯大学达拉斯分校)

Avrim Blum, Sariel Har-Peled, Benjamin Raichel

摘要:

$ \newcommand{\kalg}{k_{\mathrm{alg}}} \newcommand{\kopt}{k_{\mathrm{opt}}} \newcommand{\algset}{T} \renewcommand{\Re}{\mathbb{R}} \newcommand{\eps}{\varepsilon} \newcommand{\pth}[2][\!]{#1\left({#2}\right)} \newcommand{\npoints}{n} \newcommand{\ballD}{\mathsf{b}} \newcommand{\dataset}{P} $对于单位球$\ballD \subseteq \Re^d$中的$\npoints$点的集合$\dataset$,考虑找到一个小子集$\algset \subseteq \dataset$使得其凸包$\eps$-逼近原始集合的凸包的问题。我们提出了一个有效的算法来计算这样一个$\eps'$-近似的大小$\kalg$,其中$\eps'$是$\eps$的函数,和$\kalg$是这样一个$\eps$-近似的最小大小$\kopt$的函数。令人惊讶的是,在这两个边界中对维度$d$没有依赖性。此外,$\dataset$的每个点都可以由$\algset$的点的凸组合来近似$\eps$,该凸组合是$O(1/\eps^2)$稀疏的。我们的结果可以被看作是一种稀疏,凸自动编码的方法:近似表示的数据在一个紧凑的方式使用稀疏组合的一个小子集$\algset$的原始数据。新算法可以核化,并且保持了原始输入的稀疏性。

英文摘要:

$ \newcommand{\kalg}{k_{\mathrm{alg}}} \newcommand{\kopt}{k_{\mathrm{opt}}} \newcommand{\algset}{T} \renewcommand{\Re}{\mathbb{R}} \newcommand{\eps}{\varepsilon} \newcommand{\pth}[2][\!]{#1\left({#2}\right)} \newcommand{\npoints}{n} \newcommand{\ballD}{\mathsf{b}} \newcommand{\dataset}{P} $ For a set $\dataset$ of $\npoints$ points in the unit ball $\ballD \subseteq \Re^d$, consider the problem of finding a small subset $\algset \subseteq \dataset$ such that its convex-hull $\eps$-approximates the convex-hull of the original set. We present an efficient algorithm to compute such a $\eps'$-approximation of size $\kalg$, where $\eps'$ is function of $\eps$, and $\kalg$ is a function of the minimum size $\kopt$ of such an $\eps$-approximation. Surprisingly, there is no dependency on the dimension $d$ in both bounds. Furthermore, every point of $\dataset$ can be $\eps$-approximated by a convex-combination of points of $\algset$ that is $O(1/\eps^2)$-sparse. Our result can be viewed as a method for sparse, convex autoencoding: approximately representing the data in a compact way using sparse combinations of a small subset $\algset$ of the original data. The new algorithm can be kernelized, and it preserves sparsity in the original input.

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。

↑