English

Accelerated Primal-Dual Proximal Block Coordinate Updating Methods for Constrained Convex Optimization

Optimization and Control 2017-11-22 v3 Numerical Analysis Machine Learning

Abstract

Block Coordinate Update (BCU) methods enjoy low per-update computational complexity because every time only one or a few block variables would need to be updated among possibly a large number of blocks. They are also easily parallelized and thus have been particularly popular for solving problems involving large-scale dataset and/or variables. In this paper, we propose a primal-dual BCU method for solving linearly constrained convex program in multi-block variables. The method is an accelerated version of a primal-dual algorithm proposed by the authors, which applies randomization in selecting block variables to update and establishes an O(1/t)O(1/t) convergence rate under weak convexity assumption. We show that the rate can be accelerated to O(1/t2)O(1/t^2) if the objective is strongly convex. In addition, if one block variable is independent of the others in the objective, we then show that the algorithm can be modified to achieve a linear rate of convergence. The numerical experiments show that the accelerated method performs stably with a single set of parameters while the original method needs to tune the parameters for different datasets in order to achieve a comparable level of performance.

Keywords

Cite

@article{arxiv.1702.05423,
  title  = {Accelerated Primal-Dual Proximal Block Coordinate Updating Methods for Constrained Convex Optimization},
  author = {Yangyang Xu and Shuzhong Zhang},
  journal= {arXiv preprint arXiv:1702.05423},
  year   = {2017}
}

Comments

Accepted to Computational Optimization and Applications

R2 v1 2026-06-22T18:21:26.144Z