Regularized Nonlinear Acceleration

Part of Advances in Neural Information Processing Systems 29 (NIPS 2016)

Bibtex Metadata Paper Reviews Supplemental

Authors

Damien Scieur, Alexandre d'Aspremont, Francis Bach

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 and small 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.