English

Convergence and Applications of ADMM on the Multi-convex Problems

Optimization and Control 2022-02-01 v4

Abstract

In recent years, although the Alternating Direction Method of Multipliers (ADMM) has been empirically applied widely to many multi-convex applications, delivering an impressive performance in areas such as nonnegative matrix factorization and sparse dictionary learning, there remains a dearth of generic work on proposed ADMM with a convergence guarantee under mild conditions. In this paper, we propose a generic ADMM framework with multiple coupled variables in both objective and constraints. Convergence to a Nash point is proven with a sublinear convergence rate o(1/k)o(1/k). Two important applications are discussed as special cases under our proposed ADMM framework. Extensive experiments on ten real-world datasets demonstrate the proposed framework's effectiveness, scalability, and convergence properties. We have released our code at \url{https://github.com/xianggebenben/miADMM}.

Keywords

Cite

@article{arxiv.1902.10882,
  title  = {Convergence and Applications of ADMM on the Multi-convex Problems},
  author = {Junxiang Wang and Liang Zhao},
  journal= {arXiv preprint arXiv:1902.10882},
  year   = {2022}
}

Comments

Accepted by PAKDD 2022