Matrix completion has no spurious local minimum

Advances in Neural Information Processing Systems

Volumn , Issue , 2016, Pages 2981-2989

  Ge, Rong ^a   Lee, Jason D ^b   Ma, Tengyu ^c  

^a DUKE UNIVERSITY   (United States)

^b UNIVERSITY OF SOUTHERN CALIFORNIA   (United States)

^c PRINCETON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COLLABORATIVE FILTERING; CONVEX OPTIMIZATION; LEARNING SYSTEMS; MATRIX ALGEBRA; POLYNOMIAL APPROXIMATION; STOCHASTIC SYSTEMS;

GEOMETRIC PROPERTIES; MACHINE LEARNING PROBLEM; NOISY OBSERVATIONS; NON-CONVEX OBJECTIVE FUNCTIONS; NONCONVEX OPTIMIZATION; OPTIMIZATION ALGORITHMS; POSITIVE SEMIDEFINITE MATRICES; STATISTICAL PROBLEMS;

OPTIMIZATION;

EID: 85015153890     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (28)

1. Yonatan Amit, Michael Fink, Nathan Srebro, and Shimon Ullman. Uncovering shared structures in multiclass classification. In Proceedings of the 24th international conference on Machine learning, pages 17-24. ACM, 2007.
2. Afonso S Bandeira, Nicolas Boumal, and Vladislav Voroninski. On the low-rank approach for semidefinite programs arising in synchronization and community detection. arXiv preprint arXiv:1602.04426, 2016.
3. Samuel Burer and Renato DC Monteiro. A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization. Mathematical Programming, 95(2):329-357, 2003.
4. S. Bhojanapalli, B. Neyshabur, and N. Srebro. Global Optimality of Local Search for Low Rank Matrix Recovery. ArXiv e-prints, May 2016.
5. Emmanuel J Candès, Xiaodong Li, Yi Ma, and John Wright. Robust principal component analysis? Journal of the ACM (JACM), 58(3):11, 2011.
6. Emmanuel J Candès and Benjamin Recht. Exact matrix completion via convex optimization. Foundations of Computational mathematics, 9(6):717-772, 2009.
7. Emmanuel J Candès and Terence Tao. The power of convex relaxation: Near-optimal matrix completion. Information Theory, IEEE Transactions on, 56(5):2053-2080, 2010.
8. Yudong Chen and Martin J Wainwright. Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees. arXiv preprint arXiv:1509.03025, 2015.
9. Mark A Davenport, Yaniv Plan, Ewout van den Berg, and Mary Wootters. 1-bit matrix completion. Information and Inference, 3(3):189-223, 2014.
10. Rong Ge, Furong Huang, Chi Jin, and Yang Yuan. Escaping from saddle points-online stochastic gradient for tensor decomposition. arXiv:1503.02101, 2015.
11. Moritz Hardt. Understanding alternating minimization for matrix completion. In FOCS 2014. IEEE, 2014.
12. Daniel Hsu, Sham M Kakade, and Tong Zhang. A tail inequality for quadratic forms of subgaussian random vectors. Electron. Commun. Probab, 17(52):1-6, 2012.
13. Moritz Hardt and Mary Wootters. Fast matrix completion without the condition number. In COLT 2014, pages 638-678, 2014.
14. R. Imbuzeiro Oliveira. Sums of random Hermitian matrices and an inequality by Rudelson. ArXiv e-prints, April 2010.
15. Prateek Jain, Praneeth Netrapalli, and Sujay Sanghavi. Low-rank matrix completion using alternating minimization. In Proceedings of the forty-fifth annual ACM symposium on Theory of computing, pages 665-674. ACM, 2013.
16. Raghunandan H Keshavan, Andrea Montanari, and Sewoong Oh. Matrix completion from a few entries. Information Theory, IEEE Transactions on, 56(6):2980-2998, 2010.
17. Yehuda Koren. The bellkor solution to the netflix grand prize. Netflix prize documentation, 81, 2009.
18. Yuanzhi Li, Yingyu Liang, and Andrej Risteski. Recovery guarantee of weighted low-rank approximation via alternating minimization. arXiv preprint arXiv:1602.02262, 2016.
19. Jason D Lee, Max Simchowitz, Michael I Jordan, and Benjamin Recht. Gradient descent converges to minimizers. University of California, Berkeley, 1050:16 2016.
20. Po-Ling Loh and Martin J Wainwright. Support recovery without incoherence: A case for nonconvex regularization. arXiv preprint arXiv:1412.5632, 2014.
21. Po-Ling Loh and Martin J. Wainwright. Regularized m-estimators with nonconvexity: statistical and algorithmic theory for local optima. Journal of Machine Learning Research, 16:559-616, 2015.
22. Yurii Nesterov and Boris T Polyak. Cubic regularization of Newton method and its global performance. Mathematical Programming, 108(1):177-205, 2006.
23. Robin Pemantle. Nonconvergence to unstable points in urn models and stochastic approximations. The Annals of Probability, pages 698-712, 1990.
24. Benjamin Recht. A simpler approach to matrix completion. The Journal of Machine Learning Research, 12:3413-3430, 2011.
25. Jasson DM Rennie and Nathan Srebro. Fast maximum margin matrix factorization for collaborative prediction. In Proceedings of the 22nd international conference on Machine learning, pages 713-719. ACM, 2005.
26. Ruoyu Sun and Zhi-Quan Luo. Guaranteed matrix completion via nonconvex factorization. In Foundations of Computer Science (FOCS), 2015 IEEE 56th Annual Symposium on, pages 270-289. IEEE, 2015.
27. Ju Sun, Qing Qu, and John Wright. When are nonconvex problems not scary? arXiv preprint arXiv:1510.06096, 2015.
28. Tuo Zhao, Zhaoran Wang, and Han Liu. A nonconvex optimization framework for low rank matrix estimation. In Advances in Neural Information Processing Systems, pages 559-567, 2015.