A Conditional Gradient-Based Augmented Lagrangian Framework
From MaRDI portal
Abstract: This paper considers a generic convex minimization template with affine constraints over a compact domain, which covers key semidefinite programming applications. The existing conditional gradient methods either do not apply to our template or are too slow in practice. To this end, we propose a new conditional gradient method, based on a unified treatment of smoothing and augmented Lagrangian frameworks. The proposed method maintains favorable properties of the classical conditional gradient method, such as cheap linear minimization oracle calls and sparse representation of the decision variable. We prove convergence rate of our method in the objective residual and the feasibility gap. This rate is essentially the same as the state of the art CG-type methods for our problem template, but the proposed method is significantly superior to existing methods in various semidefinite programming applications.
This page was built for publication: A Conditional Gradient-Based Augmented Lagrangian Framework
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6312400)
