Skip to Main content Skip to Navigation

Matrix completion by singular value thresholding: sharp bounds

Abstract : We consider the matrix completion problem where the aim is to esti-mate 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 theo-retical 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 im-portant consequence of our result is the exact minimax optimal rates of convergence for matrix completion problem which were known until know only up to a logarithmic factor.
Document type :
Journal articles
Complete list of metadatas
Contributor : Olga Klopp <>
Submitted on : Friday, January 30, 2015 - 10:20:38 PM
Last modification on : Thursday, March 5, 2020 - 6:55:48 PM
Document(s) archivé(s) le : Saturday, September 12, 2015 - 7:17:02 AM


Files produced by the author(s)


  • HAL Id : hal-01111757, version 1
  • ARXIV : 1502.00146


Olga Klopp. Matrix completion by singular value thresholding: sharp bounds. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2015, 9 (2), pp. 2348--2369. ⟨hal-01111757⟩



Record views


Files downloads