Optimization Online


Convex Optimization with ALADIN

Boris Houska(borish***at***shanghaitech.edu.cn)
Dimitris Kouzoupis(dimitris.kouzoupis***at***imtek.uni-freiburg.de)
Yuning Jiang(jiangyn***at***shanghaitech.edu.cn)
Moritz Diehl(moritz.diehl***at***imtek.uni-freiburg.de)

Abstract: This paper presents novel convergence results for the Augmented Lagrangian based Alternating Direction Inexact Newton method (ALADIN) in the context of distributed convex optimization. It is shown that ALADIN converges for a large class of convex optimization problems from any starting point to minimizers without needing line-search or other globalization routines. Under additional regularity assumptions, ALADIN can achieve superlinear or even quadratic local convergence rates. The theoretical and practical advantages of ALADIN compared to other distributed convex optimization algorithms such as dual decomposition and the Alternating Direction Method of Multipliers (ADMM) are discussed and illustrated by numerical case studies.

Keywords: Convex Optimization, Distributed Optimization

Category 1: Convex and Nonsmooth Optimization (Convex Optimization )


Download: [PDF]

Entry Submitted: 01/19/2017
Entry Accepted: 01/19/2017
Entry Last Modified: 01/19/2017

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society