pith. sign in

arxiv: 1511.07294 · v1 · pith:KCAPWQTYnew · submitted 2015-11-23 · 📊 stat.ML

Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems

classification 📊 stat.ML
keywords blockcoordinatedescentmethodspointproblemssaddleapplications
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.