Inertial Three-Operator Splitting Method and Applications
Optimization and Control
2019-05-01 v1
Abstract
We introduce an inertial variant of the forward-Douglas-Rachford splitting and analyze its convergence. We specify an instance of the proposed method to the three-composite convex minimization template. We provide practical guidance on the selection of the inertial parameter based on the adaptive starting idea. Finally, we illustrate the practical performance of our method in various machine learning applications.
Cite
@article{arxiv.1904.12980,
title = {Inertial Three-Operator Splitting Method and Applications},
author = {Volkan Cevher and Bang Cong Vu and Alp Yurtsever},
journal= {arXiv preprint arXiv:1904.12980},
year = {2019}
}
Comments
This work is presented at SIAM Conference on Optimization (OP17) in Vancouver, British Columbia, Canada on the 23rd of May 2017 by Bang Cong Vu