fastridge

Python implementation of fast ridge regression via expectation maximization. Provides efficient joint estimation of the regularization parameter and regression coefficients without cross-validation, with O(min(n,p)) cost per EM iteration after preprocessing.

Source | Package

Publications

1. SY Tew, M Boley, DF Schmidt. (2023). "Bayes beats cross validation: fast and accurate ridge regression via expectation maximization." NeurIPS. 36