Pith. sign in

REVIEW 1 cited by

Debiasing Stochastic Gradient Descent to handle missing values

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2002.09338 v2 pith:RKLF66AK submitted 2020-02-21 math.ST stat.TH

classification math.STstat.TH
keywords algorithmdatamissinggradientstochasticvaluesconvergencelearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Stochastic gradient algorithm is a key ingredient of many machine learning methods, particularly appropriate for large-scale learning.However, a major caveat of large data is their incompleteness.We propose an averaged stochastic gradient algorithm handling missing values in linear models. This approach has the merit to be free from the need of any data distribution modeling and to account for heterogeneous missing proportion.In both streaming and finite-sample settings, we prove that this algorithm achieves convergence rate of $\mathcal{O}(\frac{1}{n})$ at the iteration $n$, the same as without missing values. We show the convergence behavior and the relevance of the algorithm not only on synthetic data but also on real data sets, including those collected from medical register.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Optimal Transport with Heterogeneously Missing Data

    stat.ML 2025-05 conditional novelty 6.0 of 10

    A debiased Bures-Wasserstein estimator and a matrix-completion based estimator for entropic optimal transport are consistent under heterogeneous MCAR missingness.

Pith tools