Goto

Collaborating Authors

 Mehmet Fatih Sahin



An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints

Neural Information Processing Systems

We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex problems with nonlinear constraints. We characterize the total computational complexity of our method subject to a verifiable geometric condition, which is closely related to the Polyak-Lojasiewicz and Mangasarian-Fromowitz conditions.