On some aspects of approximation of ridge functions

被引:4
|
作者
Kolleck, Anton [1 ]
Vybiral, Jan [2 ]
机构
[1] Tech Univ Berlin, Math Inst, D-10623 Berlin, Germany
[2] Charles Univ Prague, Dept Math Anal, Prague 18600 8, Czech Republic
关键词
Ridge functions; High-dimensional function approximation; Noisy measurements; Compressed sensing; Dantzig selector; RESTRICTED ISOMETRY PROPERTY; HIGH DIMENSIONS; RANDOM MATRICES; RECONSTRUCTION;
D O I
10.1016/j.jat.2015.01.003
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
We present effective algorithms for uniform approximation of multivariate functions satisfying some prescribed inner structure. We extend, in several directions, the analysis of recovery of ridge functions f (x) = g (< a, x >) as performed earlier by one of the authors and his coauthors. We consider ridge functions defined on the unit cube [-1, 1](d) as well as recovery of ridge functions defined on the unit ball from noisy measurements. We conclude with the study of functions of the type f (x) = g (parallel to a - x parallel to(2)(l2d)). (C) 2015 Elsevier Inc. All rights reserved.
引用
收藏
页码:35 / 61
页数:27
相关论文
共 50 条