Tran Dinh, QuocCevher, Volkan2014-09-292014-09-292014-09-292014https://infoscience.epfl.ch/handle/20.500.14299/107064We introduce a model-based excessive gap technique to analyze first-order primal- dual methods for constrained convex minimization. As a result, we construct new primal-dual methods with optimal convergence rates on the objective residual and the primal feasibility gap of their iterates separately. Through a dual smoothing and prox-function selection strategy, our framework subsumes the augmented Lagrangian, and alternating methods as special cases, where our rates apply.Primal-dual methodexcessive gap techniqueconstrained convex optimizationml-aiConstrained convex minimization via model-based excessive gaptext::conference output::conference paper not in proceedings