English

D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems

Machine Learning 2019-12-02 v1 Optimization and Control Machine Learning

Abstract

Decentralized optimization algorithms have attracted intensive interests recently, as it has a balanced communication pattern, especially when solving large-scale machine learning problems. Stochastic Path Integrated Differential Estimator Stochastic First-Order method (SPIDER-SFO) nearly achieves the algorithmic lower bound in certain regimes for nonconvex problems. However, whether we can find a decentralized algorithm which achieves a similar convergence rate to SPIDER-SFO is still unclear. To tackle this problem, we propose a decentralized variant of SPIDER-SFO, called decentralized SPIDER-SFO (D-SPIDER-SFO). We show that D-SPIDER-SFO achieves a similar gradient computation cost---that is, O(ϵ3)\mathcal{O}(\epsilon^{-3}) for finding an ϵ\epsilon-approximate first-order stationary point---to its centralized counterpart. To the best of our knowledge, D-SPIDER-SFO achieves the state-of-the-art performance for solving nonconvex optimization problems on decentralized networks in terms of the computational cost. Experiments on different network configurations demonstrate the efficiency of the proposed method.

Keywords

Cite

@article{arxiv.1911.12665,
  title  = {D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems},
  author = {Taoxing Pan and Jun Liu and Jie Wang},
  journal= {arXiv preprint arXiv:1911.12665},
  year   = {2019}
}
R2 v1 2026-06-23T12:30:01.116Z