A dual approach for optimal algorithms in distributed optimization over networks

César A. Uribe, Soomin Lee, Alexander Gasnikov, Angelia Nedić

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

We study dual-based algorithms for distributed convex optimization problems over networks, where the objective is to minimize a sum (Formula presented.) of functions over in a network. We provide complexity bounds for four different cases, namely: each function (Formula presented.) 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.

Original languageEnglish (US)
JournalOptimization Methods and Software
DOIs
StateAccepted/In press - 2020
Externally publishedYes

Keywords

  • 90C25
  • 90C30
  • 90C35
  • 90C60
  • Distributed optimization
  • convex optimization
  • optimal rates
  • optimization over networks
  • primal–dual algorithms

ASJC Scopus subject areas

  • Software
  • Control and Optimization
  • Applied Mathematics

Fingerprint Dive into the research topics of 'A dual approach for optimal algorithms in distributed optimization over networks'. Together they form a unique fingerprint.

Cite this