AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters

Zeyuan Allen-Zhu, Yang Yuan, Karthik Sridharan

NeurIPS 2016 · Optimization › Nonconvex and smooth optimization · approach: Stochastic variance reduction · 16 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 raw clustering in SVRG-style estimator (ClusterSVRG) vs SVRG/SAGA at large lambdaClusterSVRG · Covtype/SensIT ridge/Lassoconvergence vs #grad/nImproved
use clustering in accelerated method (ClusterACDM) vs ACDM and others at small lambdaClusterACDM · Covtype/SensITconvergence vs #grad/nImproved
apply cluster methods on poorly clusterable dataClusterSVRG and ClusterACDM · News20convergence vs #grad/nNo clear effect
use clustering with smaller diameter delta (ablation)ClusterSVRG · Covtype/SensITconvergenceImproved
use clustering with larger diameter delta (ablation)ClusterACDM · Covtype/SensITconvergenceImproved
vary clustering quality across 7 clusterings (ablation)ClusterSVRG and ClusterACDM · SensIT, CovtypeconvergenceNo clear effect
add clustering preprocessing costClusterSVRG · Covtype/SensITpreprocessing time: 3 passes of SAGANo 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