Fast Factorization of High-Dimensional Tensor Product Matrices

The 'tensorEVD' R-package offers tools for calculation and factorization of high-dimensional tensor products (Hadamard and Kronecker) that are formed by smaller matrices.

Funding: NSF PGRP-Tech Grant 2035472.

Last update: Jun 23, 2026

Installation

Installation of 'tensorEVD' package requires an R-version ≥ 3.6.0.

From CRAN (stable version)

install.packages('tensorEVD', repos='https://cran.r-project.org/')  
library(tensorEVD)                                                  

From GitHub (developing version)

if(!'remotes' %in% rownames(installed.packages())){
  install.packages('remotes', repos='https://cran.r-project.org/')  
}
# remotes::install_github('MarcooLopez/tensorEVD')
install.packages("tensorEVD", repos = c('https://marcoolopez.r-universe.dev', 'https://cloud.r-project.org'))                    
library(tensorEVD)                                                

Documentation

Description of the package's main functions.

help(package='tensorEVD', help_type='html')

Examples

Here we present examples on the use of the functions included in the package.

• Hadamard product
• Kronecker product
• Tensor EVD

Application

We provide benchmarks and an application in Genomic Prediction of the tensorEVD() function using data from the Genomes-to-Field (G2F) Initiative

• Lopez-Cruz et al., 2024. G3:Genes|Genomes|Genetics [Manuscript] [Documentation]

Citation

Lopez-Cruz M, Pérez-Rodríguez Paulino, and de los Campos G. 2024. A fast algorithm to factorize high-dimensional Tensor Product matrices used in Genetic Models. G3 Genes|Genomes|Genetics 14(3): 1-8. doi: 10.1093/g3journal/jkae001