English

Benign landscape for Burer-Monteiro factorizations of MaxCut-type semidefinite programs

Optimization and Control 2025-03-27 v2 Computational Complexity Machine Learning

Abstract

We consider MaxCut-type semidefinite programs (SDP) which admit a low rank solution. To numerically leverage the low rank hypothesis, a standard algorithmic approach is the Burer-Monteiro factorization, which allows to significantly reduce the dimensionality of the problem at the cost of its convexity. We give a sharp condition on the conditioning of the Laplacian matrix associated with the SDP under which any second-order critical point of the non-convex problem is a global minimizer. By applying our theorem, we improve on recent results about the correctness of the Burer-Monteiro approach on Z2\mathbb{Z}_2-synchronization problems and the Kuramoto model.

Keywords

Cite

@article{arxiv.2411.03103,
  title  = {Benign landscape for Burer-Monteiro factorizations of MaxCut-type semidefinite programs},
  author = {Faniriana Rakoto Endor and Irène Waldspurger},
  journal= {arXiv preprint arXiv:2411.03103},
  year   = {2025}
}
R2 v1 2026-06-28T19:48:55.874Z