Guaranteed Matrix Completion via Nonconvex Factorization

Ruoyu Sun, Zhi Quan Luo

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Matrix factorization is a popular approach for large-scale matrix completion. In this approach, the unknown low-rank matrix is expressed as the product of two much smaller matrices so that the low-rank property is automatically fulfilled. The resulting optimization problem, even with huge size, can be solved (to stationary points) very efficiently through standard optimization algorithms such as alternating minimization and stochastic gradient descent (SGD). However, due to the non-convexity caused by the factorization model, there is a limited theoretical understanding of whether these algorithms will generate a good solution. In this paper, we establish a theoretical guarantee for the factorization based formulation to correctly recover the underlying low-rank matrix. In particular, we show that under similar conditions to those in previous works, many standard optimization algorithms converge to the global optima of the factorization based formulation, and recover the true low-rank matrix. A major difference of our work from the existing results is that we do not need resampling (i.e., Using independent samples at each iteration) in either the algorithm or its analysis. To the best of our knowledge, our result is the first one that provides exact recovery guarantee for many standard algorithms such as gradient descent, SGD and block coordinate gradient descent.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE 56th Annual Symposium on Foundations of Computer Science, FOCS 2015
PublisherIEEE Computer Society
Number of pages20
ISBN (Electronic)9781467381918
StatePublished - Dec 11 2015
Externally publishedYes
Event56th IEEE Annual Symposium on Foundations of Computer Science, FOCS 2015 - Berkeley, United States
Duration: Oct 17 2015Oct 20 2015

Publication series

NameProceedings - Annual IEEE Symposium on Foundations of Computer Science, FOCS
ISSN (Print)0272-5428


Other56th IEEE Annual Symposium on Foundations of Computer Science, FOCS 2015
Country/TerritoryUnited States


  • matrix completion
  • matrix factorization
  • nonconvex optimization
  • perturbation analysis

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'Guaranteed Matrix Completion via Nonconvex Factorization'. Together they form a unique fingerprint.

Cite this