IMR: Incomplete Matrix Regression

A framework for matrix completion and regression on response matrices with missing values. The model estimates missing entries using any combination of intercepts, row and column covariates, and a low-rank matrix approximation. It applies Lasso penalties on the covariates and a nuclear norm penalty on the low-rank component. It also adjusts for correlation within the rows and columns of the target matrix using similarity matrices. The framework is described in Fouda, Labbe and Oualkacha (2026) <doi:10.48550/arXiv.2606.26325>.

Version:	1.0.0
Depends:	R (≥ 3.5)
Imports:	fields, irlba, MASS, Matrix, methods, parallel, Rcpp, RSpectra, stats, utils
LinkingTo:	Rcpp, RcppArmadillo
Suggests:	knitr, rmarkdown, spelling, testthat (≥ 3.0.0)
Published:	2026-07-10
DOI:	10.32614/CRAN.package.IMR
Author:	Khaled Fouda [aut, cre], Aurélie Labbe [ths, ctb], Karim Oualkacha [ths, ctb], Korbinian Strimmer [cph, ctb] (Authored original fast.svd R implementation in the corpcor package)
Maintainer:	Khaled Fouda <khaled.fouda at hec.ca>
BugReports:	https://github.com/khaledfouda/IMR/issues
License:	GPL (≥ 3)
URL:	https://github.com/khaledfouda/IMR
NeedsCompilation:	yes
SystemRequirements:	C++17
Language:	en-US
Citation:	IMR citation info
Materials:	README, NEWS
CRAN checks:	IMR results

Documentation:

Reference manual:	IMR.html , IMR.pdf
Vignettes:	Incomplete Matrix Regression (IMR) Vignette (source, R code)

Downloads:

Package source:	IMR_1.0.0.tar.gz
Windows binaries:	r-devel: IMR_1.0.0.zip, r-release: IMR_1.0.0.zip, r-oldrel: IMR_1.0.0.zip
macOS binaries:	r-release (arm64): IMR_1.0.0.tgz, r-oldrel (arm64): IMR_1.0.0.tgz, r-release (x86_64): IMR_1.0.0.tgz, r-oldrel (x86_64): IMR_1.0.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=IMR to link to this page.