English

An Inexact Accelerated Stochastic ADMM for Separable Convex Optimization

Optimization and Control 2020-10-27 v1

Abstract

An inexact accelerated stochastic Alternating Direction Method of Multipliers (AS-ADMM) scheme is developed for solving structured separable convex optimization problems with linear constraints. The objective function is the sum of a possibly nonsmooth convex function and a smooth function which is an average of many component convex functions. Problems having this structure often arise in machine learning and data mining applications. AS-ADMM combines the ideas of both ADMM and the stochastic gradient methods using variance reduction techniques. One of the ADMM subproblems employs a linearization technique while a similar linearization could be introduced for the other subproblem. For a specified choice of the algorithm parameters, it is shown that the objective error and the constraint violation are O(1/k)\mathcal{O}(1/k) relative to the number of outer iterations kk. Under a strong convexity assumption, the expected iterate error converges to zero linearly. A linearized variant of AS-ADMM and incremental sampling strategies are also discussed. Numerical experiments with both stochastic and deterministic ADMM algorithms show that AS-ADMM can be particularly effective for structured optimization arising in big data applications.

Keywords

Cite

@article{arxiv.2010.12765,
  title  = {An Inexact Accelerated Stochastic ADMM for Separable Convex Optimization},
  author = {Jianchao Bai and William W. Hager and Hongchao Zhang},
  journal= {arXiv preprint arXiv:2010.12765},
  year   = {2020}
}
R2 v1 2026-06-23T19:36:38.896Z