Constructing confidence sets for the matrix completion problem

DOI10.1007/978-3-319-96941-1_7MaRDI QIDQ2417438zbMATH OpenOpenAlexFDO

Authors Alexandra Carpentier, Olga Klopp, Matthias Löffler

Publication date 12 June 2019

Full work available at URL https://arxiv.org/abs/1704.02760

zbMATH Keywords

varianceBernoulli modelstatistical inferencematrix completion problemconfidence sets

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric tolerance and confidence regions (62G15) Analysis of variance and covariance (ANOVA) (62J10)

Abstract: In the present note we consider the problem of constructing honest and adaptive confidence sets for the matrix completion problem. For the Bernoulli model with known variance of the noise we provide a realizable method for constructing confidence sets that adapt to the unknown rank of the true matrix.

Recommendations

• Adaptive confidence sets for matrix completion
• Noisy low-rank matrix completion with general sampling distribution
• On signal detection and confidence sets for low rank inference problems
• Inference and uncertainty quantification for noisy matrix completion
• Adaptive multinomial matrix completion

Cited in

(2)

• On signal detection and confidence sets for low rank inference problems
• Adaptive confidence sets for matrix completion

This page was built for publication: Constructing confidence sets for the matrix completion problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2417438)