Constrained convex minimization via model-based excessive gap
Quoc Tran-Dinh · Volkan Cevher

Wed Dec 10th 07:00 -- 11:59 PM @ Level 2, room 210D #None

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.

Author Information

Quoc Tran-Dinh (LIONS, EPFL, Switzerland)
Volkan Cevher (EPFL)

More from the Same Authors