Matrix Completion has No Spurious Local Minimum

@inproceedings{Ge2016MatrixCH,
  title={Matrix Completion has No Spurious Local Minimum},
  author={Rong Ge and Jason D. Lee and Tengyu Ma},
  booktitle={NIPS},
  year={2016}
}
Matrix completion is a basic machine learning problem that has wide applications, especially in collaborative filtering and recommender systems. Simple non-convex optimization algorithms are popular and effective in practice. Despite recent progress in proving various non-convex algorithms converge from a good initial point, it remains unclear why random or arbitrary initialization suffices in practice. We prove that the commonly used non-convex objective function for matrix completion has no… CONTINUE READING
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 225 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 96 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 147 extracted citations

Symmetry. Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization

2018 Information Theory and Applications Workshop (ITA) • 2018
View 6 Excerpts
Highly Influenced

225 Citations

0501002016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 225 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…