AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Naive imputation implicitly regularizes high-dimensional linear models

Alexis Ayme, Claire Boyer, Aymeric Dieuleveut, Erwan Scornet

ICML 2023 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional linear regression theory · 1 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
zero imputation of missing inputs before linear regressionlinear models on Ho-MCAR data · theory (high-dimensional linear model)imputation biasMixed
averaged SGD on zero-imputed data with d >> sqrt(n)zero-imputed linear regression · theory (generalization bound)excess riskImproved
ridge regression instead of SGD on zero-imputed datazero-imputed linear model · Ho-MCAR spiked model, large dpredictive errorImproved
ICE imputer instead of zero imputationtwo-step linear predictors · Ho-MCAR Gaussian, low-rank and spikedpredictive performanceImproved
zero imputation vs ICE in computational costzero imputation · Ho-MCAR experimentscomputational complexityImproved
zero imputation with SGD vs specific methods (pattern-by-pattern, NeuMiss) on self-masked MNAR datatwo-step strategies · self-masking MNARpredictive performance at large dImproved

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