AI Paper Atlas

Research map / Optimization / Optimizers

Beating SGD Saturation with Tail-Averaging and Minibatching

Nicole Muecke, Gergely Neu, Lorenzo Rosasco

NeurIPS 2019 · Optimization › Optimizers · approach: SGD momentum and step-size schedules · 11 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 non-trivial tail averaging instead of uniform averaging (ablation)SGD · Least squares learning with r>1/2excess risk rate: \left(\frac{1}{\gamma T}\right)^{2 \min(r,1/2)+1} -> \left(\frac{1}{\gamma T}\right)^{2r+1}Improved
Increase smoothness r beyond 1/2 while using uniform averaging (ablation)Uniformly averaged SGD · Synthetic data, excess risk versus rexcess riskNo clear effect
Increase smoothness r beyond 1/2 while using tail averaging (ablation)Tail-averaged SGD · Synthetic data, excess risk versus rexcess riskImproved
Increase minibatch size while tail averaging (ablation)Tail-averaged SGD · Synthetic data, single passexcess riskImproved
Use tail averaging with a constant stepsize and smaller minibatch than the compared multi-pass method (ablation)Minibatch SGD · Least squares learningexcess risk rate: n^{-\frac{2r+1}{2r+1+\nu}}Improved

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