Faster Lagrangian-Based Methods in Convex Optimization
Faster Lagrangian-Based Methods in Convex Optimization
In this paper, we aim at unifying, simplifying, and improving the convergence rate analysis of Lagrangian-based methods for convex optimization problems. We first introduce the notion of nice primal algorithmic map, which plays a central role in the unification and in the simplification of the analysis of most Lagrangian-based methods. …