AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Random Reshuffling is Not Always Better

Christopher M De Sa

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 6 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
switch from with-replacement to random reshuffling (parallel SGD with averaging)Parallel SGD (Algorithm 1) · Matrix-completion-like task, n=40, M=1000loss gap over 100 epochsHurt
use random reshuffling instead of with-replacement with the same small step sizeParallel SGD · Noiseless convex quadraticsdistance to optimumImproved
use random reshuffling with separately tuned best step sizesParallel SGD, M=100 · Convex task n=8, K=20distance to optimumHurt
remove averaging (M=1, plain SGD) (ablation)Parallel SGD · Convex task n=8distance to optimumMixed
use random reshuffling in plain SGD without averagingSGD, step size 1/2 · Constructed 3-matrix plus R task, 20 runs, 1000 epochslossHurt

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