English

Convergence analysis of the stochastic reflected forward-backward splitting algorithm

Optimization and Control 2021-02-18 v1

Abstract

We propose and analyze the convergence of a novel stochastic algorithm for solving monotone inclusions that are the sum of a maximal monotone operator and a monotone, Lipschitzian operator. The propose algorithm requires only unbiased estimations of the Lipschitzian operator. We obtain the rate O(log(n)/n)\mathcal{O}(log(n)/n) in expectation for the strongly monotone case, as well as almost sure convergence for the general case. Furthermore, in the context of application to convex-concave saddle point problems, we derive the rate of the primal-dual gap. In particular, we also obtain O(1/n)\mathcal{O}(1/n) rate convergence of the primal-dual gap in the deterministic setting.

Keywords

Cite

@article{arxiv.2102.08906,
  title  = {Convergence analysis of the stochastic reflected forward-backward splitting algorithm},
  author = {Nguyen Van Dung and Bang Cong Vu},
  journal= {arXiv preprint arXiv:2102.08906},
  year   = {2021}
}
R2 v1 2026-06-23T23:15:30.597Z