Distributed Proximal Splitting Algorithms with Rates and Acceleration

Published in Frontiers in Signal Processing, 2022

Paper · arXiv · Poster · OPT 2020 · Journal · Cite

Abstract:

We propose new generic distributed proximal splitting algorithms, well suited for large-scale convex nonsmooth optimization. We derive sublinear and linear convergence results with new nonergodic rates, as well as new accelerated versions of the algorithms, using varying stepsizes.