Saved in:
Bibliographic Details
Main Authors: Endor, Faniriana Rakoto, Waldspurger, Irène
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.03103
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917968147906560
author Endor, Faniriana Rakoto
Waldspurger, Irène
author_facet Endor, Faniriana Rakoto
Waldspurger, Irène
contents 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 $\mathbb{Z}_2$-synchronization problems and the Kuramoto model.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03103
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Benign landscape for Burer-Monteiro factorizations of MaxCut-type semidefinite programs
Endor, Faniriana Rakoto
Waldspurger, Irène
Optimization and Control
Computational Complexity
Machine Learning
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 $\mathbb{Z}_2$-synchronization problems and the Kuramoto model.
title Benign landscape for Burer-Monteiro factorizations of MaxCut-type semidefinite programs
topic Optimization and Control
Computational Complexity
Machine Learning
url https://arxiv.org/abs/2411.03103