Optimization Online


Regularized nonlinear acceleration

Damien Scieur(damien.scieur***at***inria.fr)
Alexandre d'Aspremont(aspremon***at***ens.fr)
Francis Bach(francis.bach***at***inria.fr)

Abstract: We describe a convergence acceleration technique for generic optimization problems. Our scheme computes estimates of the optimum from a nonlinear average of the iterates produced by any optimization method. The weights in this average are computed via a simple linear system, whose solution can be updated online. This acceleration scheme runs in parallel to the base algorithm, providing improved estimates of the solution on the fly, while the original optimization method is running. Numerical experiments are detailed on classical classification problems.

Keywords: Acceleration

Category 1: Convex and Nonsmooth Optimization (Convex Optimization )

Category 2: Nonlinear Optimization (Unconstrained Optimization )


Download: [PDF]

Entry Submitted: 09/14/2016
Entry Accepted: 09/14/2016
Entry Last Modified: 09/14/2016

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