English

Distributed Proximal Splitting Algorithms with Rates and Acceleration

Optimization and Control 2022-01-28 v3 Machine Learning Numerical Analysis Numerical Analysis

Abstract

We analyze several generic proximal splitting algorithms well suited for large-scale convex nonsmooth optimization. We derive sublinear and linear convergence results with new rates on the function value suboptimality or distance to the solution, as well as new accelerated versions, using varying stepsizes. In addition, we propose distributed variants of these algorithms, which can be accelerated as well. While most existing results are ergodic, our nonergodic results significantly broaden our understanding of primal-dual optimization algorithms.

Keywords

Cite

@article{arxiv.2010.00952,
  title  = {Distributed Proximal Splitting Algorithms with Rates and Acceleration},
  author = {Laurent Condat and Grigory Malinovsky and Peter Richtárik},
  journal= {arXiv preprint arXiv:2010.00952},
  year   = {2022}
}
R2 v1 2026-06-23T18:58:01.919Z