Classification Gradient Boosted Trees
Gradient boosted trees classification is the special case of gradient
boosted trees. For more details, see Gradient Boosted Trees.
Details
Given n feature vectors
of n
p-dimensional feature vectors and a vector of class labels
, where
and
C is the number of classes, which describes the class to which the
feature vector
belongs, the problem is to build a gradient
boosted trees classifier.
Training Stage
Gradient boosted trees classification follows the algorithmic
framework of gradient boosted trees training. For a classification
problem with K classes, K regression trees are constructed on each
iteration, one for each output class. The loss function is
cross-entropy (multinomial deviance):
where 
Binary classification is a special case when single regression tree is trained on each iteration. The loss function is
where 
Prediction Stage
Given the gradient boosted trees classifier model and vectors
, the problem is to calculate labels for
those vectors. To solve the problem for each given feature vector
, the algorithm finds the leaf node in a tree in the
ensemble, and the leaf node gives the tree response. The algorithm
computes a sum of responses of all the trees for each class and
chooses the label y corresponding to the class with the maximal
response value (highest class probability).
Usage of Training Alternative
To build a Gradient Boosted Trees Classification model using methods of the Model Builder class of Gradient Boosted Tree Classification,
complete the following steps:
- Create a Gradient Boosted Tree Classification model builder using a constructor with the required number of classes and trees.
- Create a decision tree and add nodes to it:
- Use thecreateTreemethod with the required number of nodes in a tree and a label of the class for which the tree is created.
- Use theaddSplitNodeand addLeafNode methods to add split and leaf nodes to the created tree. See the note below describing the decision tree structure.
- After you add all nodes to the current tree, proceed to creating the next one in the same way.
- Use thegetModelmethod to get the trained Gradient Boosted Trees Classification model after all trees have been created.
Each tree consists of internal nodes (called non-leaf or split nodes) and external nodes (leaf nodes).
Each split node denotes a feature test that is a Boolean expression, for example,
f <
featureValue
or f = featureValue
, where f is a feature and featureValue
is a constant.
The test type depends on the feature type: continuous, categorical, or ordinal.
For more information on the test types, see Decision Tree.The inducted decision tree is a binary tree, meaning that each non-leaf node has exactly two branches: true and false.
Each split node contains featureIndex, the index of the feature used for the feature test in this node,
and
featureValue
, the constant for the Boolean expression in the test.
Each leaf node contains a classLabel, the predicted class for this leaf.
For more information on decision trees, see Decision Tree.Add nodes to the created tree in accordance with the pre-calculated structure of the tree.
Check that the leaf nodes do not have children nodes and that the splits have exactly two children.
Examples
C++ (CPU)
Java*
There is no support for Java on GPU.
Python*
Batch Processing
Gradient boosted trees classification follows the general workflow
described in Gradient Boosted Trees and Classification Usage Model
Training
In addition to parameters of the gradient boosted trees described
in Batch Processing, the gradient boosted trees classification training algorithm has
the following parameters:
Parameter | Default Value | Description |
---|---|---|
algorithmFPType | float | The floating-point type that the algorithm uses for intermediate computations. Can be float or double . |
method | defaultDense | The computation method used by the gradient boosted trees regression.
The only training method supported so far is the default dense method. |
nClasses | Not applicable | The number of classes. A required parameter. |
loss | crossEntropy | Loss function type. |
Prediction
In addition to the parameters of a classifier, the gradient boosted
trees classifier has the following parameters at the prediction stage:
Parameter | Default Value | Description |
---|---|---|
algorithmFPType | float | The floating-point type that the algorithm uses for intermediate computations. Can be float or double . |
method | defaultDense | The computation method used by the gradient boosted trees regression.
The only training method supported so far is the default dense method. |
nClasses | Not applicable | The number of classes. A required parameter. |
numIterations | An integer parameter that indicates how many trained iterations of the
model should be used in prediction. The default value |
Examples
C++ (CPU)
Batch Processing:
Java*
There is no support for Java on GPU.
Batch Processing:
Python*
Batch Processing: