English

Second-order Guarantees of Distributed Gradient Algorithms

Optimization and Control 2020-05-26 v5 Distributed, Parallel, and Cluster Computing

Abstract

We consider distributed smooth nonconvex unconstrained optimization over networks, modeled as a connected graph. We examine the behavior of distributed gradient-based algorithms near strict saddle points. Specifically, we establish that (i) the renowned Distributed Gradient Descent (DGD) algorithm likely converges to a neighborhood of a Second-order Stationary (SoS) solution; and (ii) the more recent class of distributed algorithms based on gradient tracking--implementable also over digraphs--likely converges to exact SoS solutions, thus avoiding (strict) saddle-points. Furthermore, new convergence rate results to first-order critical points is established for the latter class of algorithms.

Keywords

Cite

@article{arxiv.1809.08694,
  title  = {Second-order Guarantees of Distributed Gradient Algorithms},
  author = {Amir Daneshmand and Gesualdo Scutari and Vyacheslav Kungurtsev},
  journal= {arXiv preprint arXiv:1809.08694},
  year   = {2020}
}

Comments

Final version, to appear on SIAM J. on Optimization

R2 v1 2026-06-23T04:15:38.530Z