AI Paper Atlas

Research map / Optimization / Distributed and compressed

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction

Boyue Li, Shicong Cen, Yuxin Chen, Yuejie Chi

JMLR 2020 · Optimization › Distributed and compressed · approach: Decentralized optimization algorithms · 79 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Network-DANE / Network-SVRG/SARAH instead of DGD and EXTRAdecentralized optimization · synthetic linear regression, kappa=10 and 10^4communication roundsImproved
add variance-reduced local updates (Network-SVRG/SARAH) over Network-DANENetwork-DANE · synthetic linear regressiongradient evaluationsImproved
increase mixing rounds K per iteration (ablation)Network-DANE and Network-SVRG · poorly connected graph (alpha_0 = 0.944)iterations to convergeImproved
increase mixing rounds K beyond a threshold (ablation)Network-DANE and Network-SVRG · poorly connected graph (alpha_0 = 0.944)communication roundsNo clear effect
increase local iterations S for Network-SVRG up to about 0.05m (ablation)Network-SVRG · synthetic linear regression, kappa=10communication roundsImproved
use less connected topology (grid, star, ring vs Erdos-Renyi p=0.3) (ablation)Network-DANE and Network-SVRG/SARAH · synthetic linear regression, kappa=10convergenceHurt
use Network-DANE instead of ADMM and PG-EXTRAnonsmooth composite optimization · l1-regularized linear regressionconvergenceImproved
use Network-SVRG/SARAH instead of DSGD and ADMMneural network training · MNIST, one hidden layer, 20 agentscommunication and computation efficiencyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy