首页    期刊浏览 2024年12月15日 星期日
登录注册

文章基本信息

  • 标题:Matrix completion by singular value thresholding: Sharp bounds
  • 本地全文:下载
  • 作者:Olga Klopp
  • 期刊名称:Electronic Journal of Statistics
  • 印刷版ISSN:1935-7524
  • 出版年度:2015
  • 卷号:9
  • 期号:2
  • 页码:2348-2369
  • DOI:10.1214/15-EJS1076
  • 语种:English
  • 出版社:Institute of Mathematical Statistics
  • 摘要:We consider the matrix completion problem where the aim is to estimate a large data matrix for which only a relatively small random subset of its entries is observed. Quite popular approaches to matrix completion problem are iterative thresholding methods. In spite of their empirical success, the theoretical guarantees of such iterative thresholding methods are poorly understood. The goal of this paper is to provide strong theoretical guarantees, similar to those obtained for nuclear-norm penalization methods and one step thresholding methods, for an iterative thresholding algorithm which is a modification of the softImpute algorithm. An important consequence of our result is the exact minimax optimal rates of convergence for matrix completion problem which were know until now only up to a logarithmic factor.
国家哲学社会科学文献中心版权所有