Overview
Jerome H. Friedman is a statistician (Stanford University), one of the most influential figures in statistical machine learning. He developed gradient boosting, multivariate adaptive regression splines (MARS), projection pursuit, and CART (with Breiman, Olshen & Stone), and co-authored the textbook The Elements of Statistical Learning.
Key Contributions / Features
- glmnet / coordinate descent (Friedman-Hastie-Tibshirani 2010): fast cyclical coordinate descent for the lasso, ridge, and elastic-net regularization paths.
- Gradient boosting (Friedman 2001): the gradient-boosting-machine framework for additive tree ensembles.
- CART (Breiman, Friedman, Olshen & Stone 1984): classification and regression trees (CART).
- MARS and projection-pursuit regression; co-author of The Elements of Statistical Learning.
Related