Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems
Abstract
We consider convex-concave saddle point problems with a separable structure and non-strongly convex functions. We propose an efficient stochastic block coordinate descent method using adaptive primal-dual updates, which enables flexible parallel optimization for large-scale problems. Our method shares the efficiency and flexibility of block coordinate descent methods with the simplicity of primal-dual methods and utilizing the structure of the separable convex-concave saddle point problem. It is capable of solving a wide range of machine learning applications, including robust principal component analysis, Lasso, and feature selection by group Lasso, etc. Theoretically and empirically, we demonstrate significantly better performance than state-of-the-art methods in all these applications.
Cite
@article{arxiv.1511.07294,
title = {Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems},
author = {Zhanxing Zhu and Amos J. Storkey},
journal= {arXiv preprint arXiv:1511.07294},
year = {2015}
}
Comments
Accepted by AAAI 2016