On the Proximal Gradient Algorithm with Alternated Inertia
Optimization and Control
2018-01-18 v1 Machine Learning
Abstract
In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm with alternated inertia based on local geometric properties of the objective function. The results are put into perspective by discussions on several extensions and illustrations on common regularized problems.
Cite
@article{arxiv.1801.05589,
title = {On the Proximal Gradient Algorithm with Alternated Inertia},
author = {Franck Iutzeler and Jerome Malick},
journal= {arXiv preprint arXiv:1801.05589},
year = {2018}
}
Comments
Journal of Optimization Theory and Applications, Springer Verlag, A Para{\^i}tre