The package pGBRT implements a parallel algorithm for training gradient boosted regression trees (GBRT). The software learns an ensemble of truncated regression trees on a feature-wise distributed training set. Written in C++ with parallel/distributed communication provided by MPI, pGBRT supports efficient execution on both shared memory and cluster systems.
- Changes to previous version:
Initial Announcement on mloss.org.
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.