The non-convex Burer-Monteiro approach works on smooth semidefinite programs


Semidefinite programs (SDP’s) can be solved in polynomial time by interior point methods, but scalability can be an issue. To address this shortcoming, over a decade ago, Burer and Monteiro proposed to solve SDP’s with few equality constraints via rank-restricted, non-convex surrogates. Remarkably, for some applications, local optimization methods seem to converge to global optima of these nonconvex surrogates reliably. Although some theory supports this empirical success, a complete explanation of it remains an open question. In this paper, we consider a class of SDP’s which includes applications such as max-cut, community detection in the stochastic block model, robust PCA, phase retrieval and synchronization of rotations. We show that the low-rank Burer–Monteiro formulation of SDP’s in that class almost never has any spurious local optima.

Extracted Key Phrases

Citations per Year

Citation Velocity: 14

Averaging 14 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@inproceedings{Boumal2016TheNB, title={The non-convex Burer-Monteiro approach works on smooth semidefinite programs}, author={Nicolas Boumal and Vladislav Voroninski and Afonso S. Bandeira}, booktitle={NIPS}, year={2016} }