[SPARK-1547] Add gradient boosting algorithm to MLlib

• Type: New Feature
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.0.0
• Fix Version/s: 1.2.0
• Component/s: MLlib
• Target Version/s: 1.2.0
• Assignee: Manish Amde
• Reporter: Manish Amde
• Shepherd: Joseph K. Bradley
• Created: 21/Apr/14 00:20
• Updated: 05/Jan/15 21:40
• Resolved: 01/Nov/14 01:58

Description

This task requires adding the gradient boosting algorithm to Spark MLlib. The implementation needs to adapt the gradient boosting algorithm to the scalable tree implementation.

The tasks involves:

• Comparing the various tradeoffs and finalizing the algorithm before implementation
• Code implementation
• Unit tests
• Functional tests
• Performance tests
• Documentation

Ensembles design document (Google doc)

Issue Links

• is duplicated by: SPARK-3525 Gradient boosting in MLLib
• is required by: SPARK-5094 Python API for gradient-boosted trees
• is required by: SPARK-3703 Ensemble learning methods
• requires: SPARK-1545 Add Random Forest algorithm to MLlib
• links to: [Github] Pull Request #2607 (manishamde)