AI Paper Atlas

Research map / Optimization / Distributed and compressed

A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization

Shun Zheng, Jialei Wang, Fen Xia, Wei Xu, Tong Zhang

JMLR 2017 · Optimization › Distributed and compressed · approach: Communication complexity theory · 20 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 accelerated Acc-DADM instead of CoCoA+distributed SDCA with ProxSDCA local solver · covtype, rcv1, HIGGS, kdd2010 (L2-L1 SVM and LR)normalized duality gapImproved
set momentum nu=0 instead of theory-suggested nu (ablation)Acc-DADM · L2-L1 regularized loss minimizationconvergence smoothnessNo clear effect
increase local mini-batch sampling percentage sp (0.05, 0.20, 0.80) (ablation)Acc-DADM and CoCoA+ · SVM and LR on four datasetscommunications over 100 passesImproved
use Acc-DADM instead of CoCoA+ when scaling machinesdistributed dual coordinate ascent · scalability, lambda=1e-7communications or time to reach 1e-3 duality gapImproved
apply acceleration without smoothing to non-smooth hinge lossAcc-DADM · hinge loss SVMnormalized duality gapImproved
use CoCoA+ with large regularization lambdaCoCoA+ · large lambdanormalized duality gapNo 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