als-ncg (homepage)

NCG acceleration of ALS for computing low rank matrix factorizations for Collaborative Filtering

@mbhynes / (0)

This package contains the source code for the Apache Spark implementation of the ALS-NCG algorithm. The algorithm uses the Alternating Least Squares (ALS) algorithm as a nonlinear preconditioner to the Nonlinear Conjugate Gradient (NCG) algorithm for solving low rank matrix factorization problem, has significantly faster convergence to high accuracy solutions (Winlaw et al., ICPADS 2015). The NCG components of the code are built alongside the existing ALS implementation in Spark, and have linear scaling with the number of users/movies, as does the ALS algorithm.


Tags (No tags yet, login to add one. )


How to

This package doesn't have any releases published in the Spark Packages repo, or with maven coordinates supplied. You may have to build this package from source, or it may simply be a script. To use this Spark Package, please follow the instructions in the README.

Releases

No releases yet.