Pointwise and ergodic convergence rates of a variable metric proximal ADMM

arXiv1702.06626MaRDI QIDQ6283469FDOQ6283469

Authors: M. L. N. Gonçalves, J. G. Melo, Maicon Marques Alves 

Publication date: 21 February 2017

Abstract: In this paper, we obtain global $mathcalO(1/sqrtk)$ pointwise and $mathcalO(1/k)$ ergodic convergence rates for a variable metric proximal alternating direction method of multipliers(VM-PADMM) for solving linearly constrained convex optimization problems. The VM-PADMM can be seen as a class of ADMM variants, allowing the use of degenerate metrics (defined by noninvertible linear operators). We first propose and study nonasymptotic convergence rates of a variable metric hybrid proximal extragradient (VM-HPE) framework for solving monotone inclusions. Then, the above-mentioned convergence rates for the VM-PADMM are obtained essentially by showing that it falls within the latter framework. To the best of our knowledge, this is the first time that global pointwise (resp. pointwise and ergodic) convergence rates are obtained for the VM-PADMM (resp. VM-HPE framework).

This page was built for publication: Pointwise and ergodic convergence rates of a variable metric proximal ADMM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6283469)