English

A Dual Approach for Optimal Algorithms in Distributed Optimization over Networks

Optimization and Control 2020-03-17 v3 Distributed, Parallel, and Cluster Computing Multiagent Systems Systems and Control Machine Learning

Abstract

We study dual-based algorithms for distributed convex optimization problems over networks, where the objective is to minimize a sum i=1mfi(z)\sum_{i=1}^{m}f_i(z) of functions over in a network. We provide complexity bounds for four different cases, namely: each function fif_i is strongly convex and smooth, each function is either strongly convex or smooth, and when it is convex but neither strongly convex nor smooth. Our approach is based on the dual of an appropriately formulated primal problem, which includes a graph that models the communication restrictions. We propose distributed algorithms that achieve the same optimal rates as their centralized counterparts (up to constant and logarithmic factors), with an additional optimal cost related to the spectral properties of the network. Initially, we focus on functions for which we can explicitly minimize its Legendre-Fenchel conjugate, i.e., admissible or dual friendly functions. Then, we study distributed optimization algorithms for non-dual friendly functions, as well as a method to improve the dependency on the parameters of the functions involved. Numerical analysis of the proposed algorithms is also provided.

Keywords

Cite

@article{arxiv.1809.00710,
  title  = {A Dual Approach for Optimal Algorithms in Distributed Optimization over Networks},
  author = {César A. Uribe and Soomin Lee and Alexander Gasnikov and Angelia Nedić},
  journal= {arXiv preprint arXiv:1809.00710},
  year   = {2020}
}

Comments

This work is an extended version of the manuscript: Optimal Algorithms for Distributed Optimization arXiv:1712.00232

R2 v1 2026-06-23T03:53:04.982Z