AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

PMGT-VR: A Decentralized Proximal-Gradient Algorithmic Framework With Variance Reduction

Haishan Ye, Wei Xiong, Tong Zhang

TPAMI 2025 · Optimization › Nonconvex and smooth optimization · approach: Proximal finite-sum methods · 15 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 stochastic variance-reduced PMGT-SAGA/PMGT-LSVRG instead of full-gradient PG-EXTRA/NIDSdecentralized proximal gradient · a9a L1-logistic regressionsuboptimality vs component gradient evaluations: much fewer component gradient evaluations (no numbers given)Improved
use PMGT-VR with multi-consensus instead of PG-EXTRA on a poorly connected network (1-lambda2(W)=0.05)PMGT-SAGA/PMGT-LSVRG · a9a, 1-lambda2(W)=0.05suboptimality convergence: PG-EXTRA converges much slower when 1-lambda2(W) is smallImproved
PMGT-VR versus PG-EXTRA/NIDS in the ill-conditioned case sigma=1e-7nPMGT-SAGA/PMGT-LSVRG · a9a, sigma=1e-7nsuboptimality vs gradient evaluationsImproved
PMGT-VR versus PG-EXTRA/NIDS in communication roundsPMGT-SAGA/PMGT-LSVRG · a9a, sigma=1e-5ncommunication roundsHurt
use PMGT-SAGA instead of PG-EXTRA/NIDS when tau=250PMGT-SAGA/PMGT-LSVRG · a9a, all settingstotal cost: tau=250Improved
increase communication cost ratio tauPMGT-SAGA vs PG-EXTRA · a9a, sigma=1e-5nrelative total cost: similar at tau approx 1300 and tau approx 500Hurt
increase multi-consensus rounds K per iteration (ablation)PMGT-LSVRG · a9a, 1-lambda2(W)=0.05, sigma=1e-5n,1e-6ngradient evaluations to converge: faster at first, no further gain after a threshold while communication rises significantlyMixed
increase K in ill-conditioned case (ablation)PMGT-LSVRG · a9a, sigma=1e-7nconvergence: impact of multi-consensus is relatively smallNo clear effect

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