arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.07018math.NAcs.NAmath.FA
收藏

高维情况下广义岭函数的逼近

Approximation of Generalized Ridge Functions in High Dimensions

Technische Universität Berlin(柏林工业大学)

Sandra Keiper

AI总结:

本文研究了高维情况下广义岭函数的逼近问题,提出两种有效算法用于逼近未知线性子空间和函数的岭函数,并给出了误差界和数值比较。

摘要:

本文研究了广义岭函数(即沿$\mathbb{R}^N$中某些子流形常数的函数)的逼近问题。我们引入了线性袖函数的概念,其函数值仅取决于到未知线性子空间$L$的距离。我们提出两种有效算法,用于逼近形如$f(x)=g(\text{dist}(x,L)^2)$的线性袖函数,当线性子空间$L\subset \mathbb{R}^N$和函数$g\in C^s[0,1]$均未知时。我们为这两种算法证明了误差界,并提供了详尽的数值比较。我们进一步提出如何应用这些算法来捕捉一般袖函数,即沿某些低维子流形常数的函数。

英文摘要:

This paper studies the approximation of generalized ridge functions, namely of functions which are constant along some submanifolds of $\mathbb{R}^N$. We introduce the notion of linear-sleeve functions, whose function values only depend on the distance to some unknown linear subspace $L$. We propose two effective algorithms to approximate linear-sleeve functions $f(x)=g(\text{dist}(x,L)^2)$, when both the linear subspace $L\subset \mathbb{R}^N$ and the function $g\in C^s[0,1]$ are unknown. We will prove error bounds for both algorithms and provide an extensive numerical comparison of both. We further propose an approach of how to apply these algorithms to capture general sleeve functions, which are constant along some lower dimensional submanifolds.

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。

↑