On minimax identification of nonparametric autoregressive models

被引:0
|
作者
Bernard Delyon
Anatoli Juditsky
机构
[1] IRISA,
[2] Campus de Beaulieu,undefined
[3] 35042 Rennes Cedex,undefined
[4] France e-mail: delyon@math.univ-rennes1.fr,undefined
[5] INRIA Rhône-Alpes,undefined
[6] 655 avenue de l'Europe 38330 Montbonnot Saint Martin,undefined
[7] France e-mail: Anatoli.Iouditski@inrialpes.fr,undefined
来源
关键词
Mathematics Subject Classification (1991): 62M05, 62G07, 62M20;
D O I
暂无
中图分类号
学科分类号
摘要
We consider the problem of nonparametric identification for a multi-dimensional functional autoregression yt = f(yt−1, …,yt−d) + et on the basis of N observations of yt. In the case when the unknown nonlinear function f belongs to the Barron class, we propose an estimation algorithm which provides approximations of f with expected L2 accuracy O(N1/4ln1/4N). We also show that this approximation rate cannot be significantly improved.
引用
收藏
页码:21 / 39
页数:18
相关论文
共 50 条