文章基本信息

标题：Early stopping for statistical inverse problems via truncated SVD estimation
本地全文：下载
作者：Gilles Blanchard ; Marc Hoffmann ; Markus Reiß 等
期刊名称：Electronic Journal of Statistics
印刷版ISSN：1935-7524
出版年度：2018
卷号：12
期号：2
页码：3204-3231
DOI：10.1214/18-EJS1482
语种：English
出版社：Institute of Mathematical Statistics
摘要：We consider truncated SVD (or spectral cut-off, projection) estimators for a prototypical statistical inverse problem in dimension $D$. Since calculating the singular value decomposition (SVD) only for the largest singular values is much less costly than the full SVD, our aim is to select a data-driven truncation level $\widehat{m}\in \{1,\ldots ,D\}$ only based on the knowledge of the first $\widehat{m}$ singular values and vectors.