-

 

 

 




Optimization Online





 

Stochastic Quasi-Fejér Block-Coordinate Fixed Point Iterations with Random Sweeping

Patrick L. Combettes (plc***at***math.jussieu.fr)
Jean-Christophe Pesquet (jean-christophe.pesquet***at***univ-paris-est.fr)

Abstract: This work investigates the properties of stochastic quasi-Fejér monotone sequences in Hilbert spaces and emphasizes their pertinence in the study of the convergence of block-coordinate fixed point methods. The iterative methods under investigation feature random sweeping rules to select the blocks of variables that are activated over the course of the iterations and allow for stochastic errors in the evaluation of the operators. Algorithms using quasinonexpansive operators or compositions of nonexpansive averaged operators are constructed. The results are shown to yield novel block-coordinate operator splitting methods for solving structured monotone inclusion and convex minimization problems. In particular, the proposed framework leads to the design of random block-coordinate versions of the Douglas-Rachford and forward backward algorithms and some of their variants.

Keywords: averaged nonexpansive operator, block-coordinate algorithm, Douglas-Rachford algorithm, fixed-point algorithm, forward-backward algorithm, primal-dual operator splitting, stochastic quasi Fejér sequence, structured minimization problem

Category 1: Convex and Nonsmooth Optimization (Convex Optimization )

Category 2: Convex and Nonsmooth Optimization (Nonsmooth Optimization )

Category 3: Stochastic Programming

Citation:

Download: [PDF]

Entry Submitted: 04/29/2014
Entry Accepted: 04/29/2014
Entry Last Modified: 05/27/2014

Modify/Update this entry


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

 

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