English

On the convergence rate of the three operator splitting scheme

Machine Learning 2021-06-29 v5 Optimization and Control

Abstract

The three operator splitting scheme was recently proposed by [Davis and Yin, 2015] as a method to optimize composite objective functions with one convex smooth term and two convex (possibly non-smooth) terms for which we have access to their proximity operator. In this short note we provide an alternative proof for the sublinear rate of convergence of this method.

Cite

@article{arxiv.1610.07830,
  title  = {On the convergence rate of the three operator splitting scheme},
  author = {Fabian Pedregosa},
  journal= {arXiv preprint arXiv:1610.07830},
  year   = {2021}
}

Comments

Fixed typo in Lemma 3