Rank optimality for the Burer-Monteiro factorization
Abstract
When solving large scale semidefinite programs that admit a low-rank solution, an efficient heuristic is the Burer-Monteiro factorization: instead of optimizing over the full matrix, one optimizes over its low-rank factors. This reduces the number of variables to optimize, but destroys the convexity of the problem, thus possibly introducing spurious second-order critical points. The article [Boumal, Voroninski, and Bandeira, 2018] shows that when the size of the factors is of the order of the square root of the number of linear constraints, this does not happen: for almost any cost matrix, second-order critical points are global solutions. In this article, we show that this result is essentially tight: for smaller values of the size, second-order critical points are not generically optimal, even when the global solution is rank 1.
Cite
@article{arxiv.1812.03046,
title = {Rank optimality for the Burer-Monteiro factorization},
author = {Irène Waldspurger and Alden Waters},
journal= {arXiv preprint arXiv:1812.03046},
year = {2019}
}
Comments
Simplified results and proofs