On the Complexity of a Practical Primal-Dual Coordinate Method
Optimization and Control
2022-01-20 v1 Machine Learning
Machine Learning
Abstract
We prove complexity bounds for the primal-dual algorithm with random extrapolation and coordinate descent (PURE-CD), which has been shown to obtain good practical performance for solving convex-concave min-max problems with bilinear coupling. Our complexity bounds either match or improve the best-known results in the literature for both dense and sparse (strongly)-convex-(strongly)-concave problems.
Cite
@article{arxiv.2201.07684,
title = {On the Complexity of a Practical Primal-Dual Coordinate Method},
author = {Ahmet Alacaoglu and Volkan Cevher and Stephen J. Wright},
journal= {arXiv preprint arXiv:2201.07684},
year = {2022}
}