poismf: Factorization of Sparse Counts Matrices Through Poisson Likelihood

Creates a non-negative low-rank approximate factorization of a sparse counts matrix by maximizing Poisson likelihood with L1/L2 regularization (e.g. for implicit-feedback recommender systems or bag-of-words-based topic modeling) (Cortes, (2018) <arXiv:1811.01908>), which usually leads to very sparse user and item factors (over 90% zero-valued). Similar to hierarchical Poisson factorization (HPF), but follows an optimization-based approach with regularization instead of a hierarchical prior, and is fit through gradient-based methods instead of variational inference.

Getting started

Package details

AuthorDavid Cortes [aut, cre, cph], Jean-Sebastien Roy [cph] (Copyright holder of included tnc library), Stephen Nash [cph] (Copyright holder of included tnc library)
MaintainerDavid Cortes <david.cortes.rivera@gmail.com>
LicenseBSD_2_clause + file LICENSE
URL https://github.com/david-cortes/poismf
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the poismf package in your browser

Any scripts or data that you put into this service are public.

poismf documentation built on March 31, 2023, 7:38 p.m.