A Bayesian approach for noisy matrix completion: Optimal rate under general sampling distribution

Files in This Item:
File Description SizeFormat 
euclid.ejs.1427990076.pdf325.83 kBAdobe PDFDownload
Title: A Bayesian approach for noisy matrix completion: Optimal rate under general sampling distribution
Authors: Mai, The TienAlquier, Pierre
Permanent link: http://hdl.handle.net/10197/7050
Date: Apr-2015
Online since: 2015-09-17T09:50:04Z
Abstract: Bayesian methods for low-rank matrix completion with noise have been shown to be very efficient computationally [3, 18, 19, 24, 28]. While the behaviour of penalized minimization methods is well understood both from the theoretical and computational points of view (see [7, 9, 16, 23] among others) in this problem, the theoretical optimality of Bayesian estimators have not been explored yet. In this paper, we propose a Bayesian estimator for matrix completion under general sampling distribution. We also provide an oracle inequality for this estimator. This inequality proves that, whatever the rank of the matrix to be estimated, our estimator reaches the minimax-optimal rate of convergence (up to a logarithmic factor). We end the paper with a short simulation study.
Type of material: Journal Article
Publisher: Institute of Mathematical Statistics
Journal: Electronic Journal of Statistics
Volume: 9
Issue: 1
Start page: 823
End page: 841
Keywords: Matrix completionBayesian analysisPACBayesian boundsOracle inequalityLow-rank matrixGibbs sampler
DOI: 10.1214/15-EJS1020
Language: en
Status of Item: Peer reviewed
Appears in Collections:Mathematics and Statistics Research Collection
Insight Research Collection

Show full item record

Citations 50

Last Week
Last month
checked on Jan 18, 2020

Page view(s) 50

Last Week
Last month
checked on Jan 22, 2020


checked on Jan 22, 2020

Google ScholarTM



This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.