A graphical approach to the analysis of matrix completion

Tingni Sun, Cun Hui Zhang

Research output: Contribution to journalArticlepeer-review

Abstract

This paper considers the problem of matrix completion, which is to recover a d1×d2 matrix from observations in a small proportion of indices. We study the nuclear norm minimization method with the restriction of matching the observed entries. Under certain coherence conditions, we prove that the required sample size is of order r2dlogd via a graphical approach, where d=d1+d2 and r is the rank of the target matrix.

Original languageEnglish (US)
Pages (from-to)3935-3951
Number of pages17
JournalStochastic Processes and their Applications
Volume126
Issue number12
DOIs
StatePublished - Dec 1 2016

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'A graphical approach to the analysis of matrix completion'. Together they form a unique fingerprint.

Cite this