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

Nicolas Boumal Vladislav Voroninski Afonso S. Bandeira

Published in: CoRR (2016)

Keyphrases

semidefinite
convex relaxation
semidefinite programming
positive semidefinite
higher dimensional
convex sets
interior point methods
convex optimization
sufficient conditions
machine learning
multistage
multiple kernel learning
finite dimensional
globally optimal
linear programming
denoising
special case