Skip to content

alexandresegers/sgdGMF_Paper

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

sgdGMF_Paper

sgdGMF is an R package for efficient estimation of generalized matrix factorization (GMF) models [1,2,3]. The package implments the adaptive stochastic gradient descent with block- and coordinate-wise subsampling strategies proposed in [4]. Additionally, sgdGMF implements the alternated iterative re-weighted least squares [1,3] and diagonal-Hessian quasi-Newton [1] algorithms. The package is available at https://github.com/CristianCastiglione/sgdGMF.

This repository contains a copy of the package and all code required to replicate the results in [4].

The reproduce the results of the manuscript, one should:

Then, one can run sgdGMF_manuscript.R script to obtain all results of the paper (this can take a lot of time for some scripts - mainly for the CaseStudy).

References

[1] Collins, M., Dasgupta, S., Schapire, R.E. (2001). A generalization of principal components analysis to the exponential family. Advances in neural information processing systems, 14.

[2] Kidzinski, L., Hui, F.K.C., Warton, D.I., Hastie, T.J. (2022). Generalized Matrix Factorization: efficient algorithms for fitting generalized linear latent variable models to large data arrays. Journal of Machine Learning Research, 23(291): 1--29.

[3] Wang, L., Carvalho, L. (2023). Deviance matrix factorization. Electronic Journal of Statistics, 17(2): 3762--3810.

[4] Castiglione, C., Segers, A., Clement, L, Risso, D. (2024). Stochastic gradient descent estimation of generalized matrix factorization models with application to single-cell RNA sequencing data. arXiv preprint: arXiv:2412.20509.

About

Analyses for the sgdGMF paper

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •