AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

NeuMiss networks: differentiable programming for supervised learning with missing values.

Marine Le Morvan, Julie Josse, Thomas Moreau, Erwan Scornet, Gael Varoquaux

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 23 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 NeuMiss mask-multiplication nonlinearities instead of a classical ReLU networkNeuMiss networks · Supervised learning with missing valuespredictive accuracyImproved
Increase model capacity (ablation)NeuMiss networks · Supervised learning with missing valuespredictive accuracyImproved
Increase model capacity (ablation)Classical networks · Supervised learning with missing valuespredictive accuracyNo clear effect
Use NeuMiss instead of procedures using EM or imputationSupervised learning with missing values, including self-masking MNAR · Missing values under different missingness mechanismsrobustness to missing data mechanismImproved

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