Package: IMR 1.0.0

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>.

Authors:Khaled Fouda [aut, cre], Aurélie Labbe [ths, ctb], Karim Oualkacha [ths, ctb], Korbinian Strimmer [cph, ctb]

IMR_1.0.0.tar.gz
IMR_1.0.0.zip(r-4.7)IMR_1.0.0.zip(r-4.6)IMR_1.0.0.zip(r-4.5)
IMR_1.0.0.tgz(r-4.6-x86_64)IMR_1.0.0.tgz(r-4.6-arm64)IMR_1.0.0.tgz(r-4.5-x86_64)IMR_1.0.0.tgz(r-4.5-arm64)
IMR_1.0.0.tar.gz(r-4.7-arm64)IMR_1.0.0.tar.gz(r-4.7-x86_64)IMR_1.0.0.tar.gz(r-4.6-arm64)IMR_1.0.0.tar.gz(r-4.6-x86_64)
IMR_1.0.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
IMR/json (API)

# Install 'IMR' in R:

install.packages('IMR', repos = c('https://khaledfouda.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/khaledfouda/imr/issues

Uses libs:

openblas– Optimized BLAS
c++– GNU Standard C++ Library v3

Datasets:

Bixi_sample - Bixi Sample Data

On CRAN:

openblas cpp

5.15 score 4 scripts 15 exports 14 dependencies

Last updated from:3f4ace13e9. Checks:13 OK. Indexed: yes.

Target	Result	Time
linux-devel-arm64	OK	160
linux-devel-x86_64	OK	164
source / vignettes	OK	303
linux-release-arm64	OK	157
linux-release-x86_64	OK	167
macos-release-arm64	OK	148
macos-release-x86_64	OK	282
macos-oldrel-arm64	OK	198
macos-oldrel-x86_64	OK	253
windows-devel	OK	147
windows-release	OK	146
windows-oldrel	OK	153
wasm-release	OK	116

Exports:as_incomplete evaluate get_metric imr_convergence imr_data imr_fit imr_set_grid_limits imr_similarity imr_tune imr_tune_grid is_incomplete mc_with_means reconstruct reconstruct_partial svd_opt

Dependencies:dotCall64 fields irlba lattice maps MASS Matrix RColorBrewer Rcpp RcppArmadillo RcppEigen RSpectra spam viridisLite

Incomplete Matrix Regression (IMR) Vignette

Rendered fromIMR.Rmdusingknitr::rmarkdown

Last update: 2026-07-01
Started: 2026-04-14

Help page	Topics
Clean and convert any matrix to a sparse object	as_incomplete
Bixi Sample Data	Bixi_sample
Extract the fitted model's coefficients	coef.imr_fit
Evaluate Model Predictions	evaluate
Returns a predefined error metric	get_metric
Control Parameters for IMR Convergence	imr_convergence
Prepare Data and Model Structure for IMR	imr_data
Fit an IMR Model	imr_fit
Automatically Determine Hyperparameter Grid Maximum Values	imr_set_grid_limits
Generate Similarity or Information Matrix Object	imr_similarity
Hyperparameter Tuning for IMR Models	imr_tune
Define Hyperparameter Tuning Grid for IMR	imr_tune_grid
Has the matrix be processed by 'as_incomplete()'?	is_incomplete
Matrix Completion using Row and Column Means	mc_with_means
Summary of the model's convergence parameters	print.imr_convergence
Print an IMR data object	print.imr_data
Summary of the model's fit operation	print.imr_fit
Print an IMR similarity object	print.imr_similarity
Summary of the hyperparameter grid	print.imr_tune_grid
Reconstruct Model Estimates and Components	reconstruct
Partially Reconstruct Model Estimates for Specific Indices	reconstruct_partial
Summary of the fitted model's parameters	summary.imr_fit
Optimized Singular Value Decomposition	svd_opt
Update IMR Model Structure	update.imr_data

Package: IMR 1.0.0

IMR: Incomplete Matrix Regression

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)