flashier - Empirical Bayes Matrix Factorization
Implements empirical Bayes matrix factorization (EBMF), a
flexible modeling framework for matrix factorization based on
Wang and Stephens (2021)
<https://jmlr.org/papers/v22/20-589.html>. Includes many
popular matrix factorization methods such as SVD, sparse factor
analysis (SFA), non-negative matrix factorization (NMF) and
semi-non-negative matrix factorization (semi-NMF) as special
cases. The model fitting algorithms are implemented using a
modular computational framework that efficiently handles a
variety of data types.