Inexact Augmented Lagrangian Methods for Conic Programs: Quadratic Growth and Linear Convergence

Neural Information Processing Systems 

Under the quadratic growth assumption, it is known that the dual iterates and the Karush-Kuhn-Tucker (KKT) residuals of ALMs applied to semidefi-nite programs (SDPs) converge linearly. In contrast, the convergence rate of the primal iterates has remained elusive.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found