Distributed Proximal Splitting Algorithms with Rates and Acceleration

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.

Automated summary

We analyze several generic proximal splitting algorithms suitable for large-scale convex nonsmooth optimization and derive new convergence results and accelerated versions. We also propose distributed variants of these algorithms. Our nonergodic results significantly broaden our understanding of primal-dual optimization algorithms.