AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Debiasing Averaged Stochastic Gradient Descent to handle missing values

Aude Sportisse, Claire Boyer, Aymeric Dieuleveut, Julie Josse

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Stochastic gradient last-iterate analysis · 5 citations (OpenAlex)

Read the paper

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 EM instead of AvSGD for parameter estimationregression with missing values · Superconductivity (81 features)relative l2 prediction error: 0.7Hurt
use averaging (AvSGD) over plain SGD with decaying step (ablation)SGD for least squares with missing values · synthetic, n=10^5, d=10, 30% MCARexcess empirical riskImproved
run multiple passes instead of one pass (ablation)AvSGD · synthetic, n=10^3, 100 passesexcess empirical riskNo clear effect
ignore heterogeneous missingness probabilities in debiasing (ablation)AvSGD · synthetic, heterogeneous missing valuesexcess empirical riskHurt
use constant step size instead of decaying step size (ablation)SGD without averaging · synthetic, n=10^5excess empirical riskMixed
debias the gradient instead of mean imputation (ablation)AvSGD · Superconductivityrelative l2 prediction errorImproved

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