ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2105.01231
29
14

GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning

4 May 2021
Xin Zhang
Jia Liu
Zhengyuan Zhu
Elizabeth S. Bentley
ArXivPDFHTML
Abstract

Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity. However, three fundamental challenges in designing decentralized optimization algorithms are how to reduce their sample, communication, and memory complexities. In this paper, we propose a \underline{g}radient-\underline{t}racking-based \underline{sto}chastic \underline{r}ecursive \underline{m}omentum (GT-STORM) algorithm for efficiently solving nonconvex optimization problems. We show that to reach an ϵ2\epsilon^2ϵ2-stationary solution, the total number of sample evaluations of our algorithm is O~(m1/2ϵ−3)\tilde{O}(m^{1/2}\epsilon^{-3})O~(m1/2ϵ−3) and the number of communication rounds is O~(m−1/2ϵ−3)\tilde{O}(m^{-1/2}\epsilon^{-3})O~(m−1/2ϵ−3), which improve the O(ϵ−4)O(\epsilon^{-4})O(ϵ−4) costs of sample evaluations and communications for the existing decentralized stochastic gradient algorithms. We conduct extensive experiments with a variety of learning models, including non-convex logistical regression and convolutional neural networks, to verify our theoretical findings. Collectively, our results contribute to the state of the art of theories and algorithms for decentralized network optimization.

View on arXiv
Comments on this paper