Boosted Binary Regression Trees

Version 3.1.0.0 (5.97 KB) by Kota Hara
Boosted Binary Regression Trees is a powerful regression method which can handle vector targets.
2.6K Downloads
Updated 12 Jul 2016

View License

Boosted Binary Regression Trees (BBRT) is a powerful regression method proposed in [1]. BBRT combines binary regression trees [3] using a gradient boosting technique.
There are several variants proposed in [1]. In [1], it is assumed that the target is a scalar value. However, it is trivial to extend the method to vector target cases by proper modifications.
This code is based on "LS_Boost" described in [1] but it can also handle vector target cases. In other words, you do not need to train an independent regressor for each target dimension, unlike Support Vector Regression.
The detail of the algorithm this code implements can be found in [2].
[1] J. H. Friedman. Greedy Function Approximation: a Gradient Boosting Machine. Annals of Statistics, 2001.
[2] Kota Hara and Rama Chellappa, Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation, CVPR 2013.
[3] Breiman, Leo; Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984). Classification and regression trees. Monterey, CA: Wadsworth & Brooks/Cole Advanced Books & Software. ISBN 978-0-412-04841-8.

Cite As

Kota Hara (2024). Boosted Binary Regression Trees (https://www.mathworks.com/matlabcentral/fileexchange/42130-boosted-binary-regression-trees), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2014a
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
3.1.0.0

Added a sentence to README.txt

3.0.0.0

Added instruction with some sample data.
Speed up training.
Officially support linux.

1.5.0.0

Faster training by mex for finding the best splitting function

1.2.0.0

Slightly changed the description. No changes to the code.

1.0.0.0