Papers
Topics
Authors
Recent
Search
2000 character limit reached

Iteration complexity of first-order augmented Lagrangian methods for convex conic programming

Published 27 Mar 2018 in math.OC, cs.CC, cs.NA, and math.NA | (1803.09941v5)

Abstract: In this paper we consider a class of convex conic programming. In particular, we first propose an inexact augmented Lagrangian (I-AL) method that resembles the classical I-AL method for solving this problem, in which the augmented Lagrangian subproblems are solved approximately by a variant of Nesterov's optimal first-order method. We show that the total number of first-order iterations of the proposed I-AL method for finding an ϵ\epsilon-KKT solution is at most O(ϵ−7/4)\mathcal{O}(\epsilon^{-7/4}). We then propose an adaptively regularized I-AL method and show that it achieves a first-order iteration complexity O(ϵ−1log⁡ϵ−1)\mathcal{O}(\epsilon^{-1}\log\epsilon^{-1}), which significantly improves existing complexity bounds achieved by first-order I-AL methods for finding an ϵ\epsilon-KKT solution. Our complexity analysis of the I-AL methods is based on a sharp analysis of inexact proximal point algorithm (PPA) and the connection between the I-AL methods and inexact PPA. It is vastly different from existing complexity analyses of the first-order I-AL methods in the literature, which typically regard the I-AL methods as an inexact dual gradient method.

Authors (2)
Citations (28)

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.