arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.06016math.FA
收藏

具有正定核的采样和相应的二分法

Sampling with positive definite kernels and an associated dichotomy

Palle Jorgensen, Feng Tian

摘要:

我们研究类的再生核$K$一般域,这些都是核,通常出现在机器学习模型,模型的基础上某些家庭的再生核希尔伯特空间。它们是正定核$K$,具有存在可数离散样本子集$S$的性质;即,真子集$S$具有这样的性质,即$\mathscr{H}\left(K\right)$中的每个函数都允许$S$ -样本表示。我们给出了允许这种非平凡可数离散样本集的核的特征。一些应用程序和具体的内核中给出的文件的后半部分。

英文摘要:

We study classes of reproducing kernels $K$ on general domains; these are kernels which arise commonly in machine learning models; models based on certain families of reproducing kernel Hilbert spaces. They are the positive definite kernels $K$ with the property that there are countable discrete sample-subsets $S$; i.e., proper subsets $S$ having the property that every function in $\mathscr{H}\left(K\right)$ admits an $S$-sample representation. We give a characterizations of kernels which admit such non-trivial countable discrete sample-sets. A number of applications and concrete kernels are given in the second half of the paper.

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。

↑