Constrained convex minimization via model-based excessive gap

Part of Advances in Neural Information Processing Systems 27 (NIPS 2014)

Authors

Quoc Tran-Dinh, Volkan Cevher

Abstract

We introduce a model-based excessive gap technique to analyze first-order primal- dual methods for constrained convex minimization. As a result, we construct first- order primal-dual methods with optimal convergence rates on the primal objec- tive residual and the primal feasibility gap of their iterates separately. Through a dual smoothing and prox-center selection strategy, our framework subsumes the augmented Lagrangian, alternating direction, and dual fast-gradient methods as special cases, where our rates apply.