NeurIPS 2016oral177 citations
Regularized Nonlinear Acceleration
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.
BibTeX
@inproceedings{NIPS2016_bbf94b34,
author = {Scieur, Damien and d\textquotesingle Aspremont, Alexandre and Bach, Francis},
booktitle = {Advances in Neural Information Processing Systems},
editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Regularized Nonlinear Acceleration},
url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/bbf94b34eb32268ada57a3be5062fe7d-Paper.pdf},
volume = {29},
year = {2016}
}