English

Online Alternating Direction Method of Multipliers for Online Composite Optimization

Optimization and Control 2024-02-09 v2

Abstract

In this paper, we investigate regrets of an online semi-proximal alternating direction method of multiplier (Online-spADMM) for solving online linearly constrained convex composite optimization problems. Under mild conditions, we establish O(N){\rm O}(\sqrt{N}) objective regret and O(N){\rm O}(\sqrt{N}) constraint violation regret at round NN when the dual step-length is taken in (0,(1+5)/2)(0,(1 +\sqrt{5})/2) and penalty parameter σ\sigma is taken as N\sqrt{N}. We explain that the optimal value of parameter σ\sigma is of order O(N){\rm O}(\sqrt{N}). Like the semi-proximal alternating direction method of multiplier (spADMM), Online-spADMM has the advantage to resolve the potentially non-solvability issue of the subproblems efficiently. We show the usefulness of the obtained results when applied to different types of online optimization problems and verify the theoretical result by numerical experiments}. The inequalities established for Online-spADMM are also used to develop iteration complexity of the average update of spADMM for solving linearly constrained convex composite optimization problems.

Keywords

Cite

@article{arxiv.1904.02862,
  title  = {Online Alternating Direction Method of Multipliers for Online Composite Optimization},
  author = {Yule Zhang and Zehao Xiao and Jia Wu and Liwei Zhang},
  journal= {arXiv preprint arXiv:1904.02862},
  year   = {2024}
}
R2 v1 2026-06-23T08:29:59.195Z