High-dimensional estimation with missing data: Statistical and computational limits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Verchand, Kabir Aladin, Pensia, Ankit, Haque, Saminul, Kuditipudi, Rohith
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911523091251200
author Verchand, Kabir Aladin
Pensia, Ankit
Haque, Saminul
Kuditipudi, Rohith
author_facet Verchand, Kabir Aladin
Pensia, Ankit
Haque, Saminul
Kuditipudi, Rohith
contents We consider computationally-efficient estimation of population parameters when observations are subject to missing data. In particular, we consider estimation under the realizable contamination model of missing data in which an $ε$ fraction of the observations are subject to an arbitrary (and unknown) missing not at random (MNAR) mechanism. When the true data is Gaussian, we provide evidence towards statistical-computational gaps in several problems. For mean estimation in $\ell_2$ norm, we show that in order to obtain error at most $ρ$, for any constant contamination $ε\in (0, 1)$, (roughly) $n \gtrsim d e^{1/ρ^2}$ samples are necessary and that there is a computationally-inefficient algorithm which achieves this error. On the other hand, we show that any computationally-efficient method within certain popular families of algorithms requires a much larger sample complexity of (roughly) $n \gtrsim d^{1/ρ^2}$ and that there exists a polynomial time algorithm based on sum-of-squares which (nearly) achieves this lower bound. For covariance estimation in relative operator norm, we show that a parallel development holds. Finally, we turn to linear regression with missing observations and show that such a gap does not persist. Indeed, in this setting we show that minimizing a simple, strongly convex empirical risk nearly achieves the information-theoretic lower bound in polynomial time.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16712
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle High-dimensional estimation with missing data: Statistical and computational limits
Verchand, Kabir Aladin
Pensia, Ankit
Haque, Saminul
Kuditipudi, Rohith
Statistics Theory
Data Structures and Algorithms
Machine Learning
We consider computationally-efficient estimation of population parameters when observations are subject to missing data. In particular, we consider estimation under the realizable contamination model of missing data in which an $ε$ fraction of the observations are subject to an arbitrary (and unknown) missing not at random (MNAR) mechanism. When the true data is Gaussian, we provide evidence towards statistical-computational gaps in several problems. For mean estimation in $\ell_2$ norm, we show that in order to obtain error at most $ρ$, for any constant contamination $ε\in (0, 1)$, (roughly) $n \gtrsim d e^{1/ρ^2}$ samples are necessary and that there is a computationally-inefficient algorithm which achieves this error. On the other hand, we show that any computationally-efficient method within certain popular families of algorithms requires a much larger sample complexity of (roughly) $n \gtrsim d^{1/ρ^2}$ and that there exists a polynomial time algorithm based on sum-of-squares which (nearly) achieves this lower bound. For covariance estimation in relative operator norm, we show that a parallel development holds. Finally, we turn to linear regression with missing observations and show that such a gap does not persist. Indeed, in this setting we show that minimizing a simple, strongly convex empirical risk nearly achieves the information-theoretic lower bound in polynomial time.
title High-dimensional estimation with missing data: Statistical and computational limits
topic Statistics Theory
Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2603.16712