Random features models: a way to study the success of naive imputation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ayme, Alexis, Boyer, Claire, Dieuleveut, Aymeric, Scornet, Erwan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913224698363904
author Ayme, Alexis
Boyer, Claire
Dieuleveut, Aymeric
Scornet, Erwan
author_facet Ayme, Alexis
Boyer, Claire
Dieuleveut, Aymeric
Scornet, Erwan
contents Constant (naive) imputation is still widely used in practice as this is a first easy-to-use technique to deal with missing data. Yet, this simple method could be expected to induce a large bias for prediction purposes, as the imputed input may strongly differ from the true underlying data. However, recent works suggest that this bias is low in the context of high-dimensional linear predictors when data is supposed to be missing completely at random (MCAR). This paper completes the picture for linear predictors by confirming the intuition that the bias is negligible and that surprisingly naive imputation also remains relevant in very low dimension.To this aim, we consider a unique underlying random features model, which offers a rigorous framework for studying predictive performances, whilst the dimension of the observed features varies.Building on these theoretical results, we establish finite-sample bounds on stochastic gradient (SGD) predictors applied to zero-imputed data, a strategy particularly well suited for large-scale learning.If the MCAR assumption appears to be strong, we show that similar favorable behaviors occur for more complex missing data scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03839
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Random features models: a way to study the success of naive imputation
Ayme, Alexis
Boyer, Claire
Dieuleveut, Aymeric
Scornet, Erwan
Statistics Theory
Machine Learning
Constant (naive) imputation is still widely used in practice as this is a first easy-to-use technique to deal with missing data. Yet, this simple method could be expected to induce a large bias for prediction purposes, as the imputed input may strongly differ from the true underlying data. However, recent works suggest that this bias is low in the context of high-dimensional linear predictors when data is supposed to be missing completely at random (MCAR). This paper completes the picture for linear predictors by confirming the intuition that the bias is negligible and that surprisingly naive imputation also remains relevant in very low dimension.To this aim, we consider a unique underlying random features model, which offers a rigorous framework for studying predictive performances, whilst the dimension of the observed features varies.Building on these theoretical results, we establish finite-sample bounds on stochastic gradient (SGD) predictors applied to zero-imputed data, a strategy particularly well suited for large-scale learning.If the MCAR assumption appears to be strong, we show that similar favorable behaviors occur for more complex missing data scenarios.
title Random features models: a way to study the success of naive imputation
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2402.03839