Generalized Additive Model for Binary Classification

The documentation is generated based on the sources available at dotnet/machinelearning and released under MIT License.

Type: binaryclassifiertrainer Aliases: BinaryClassificationGamTrainer, gam Namespace: Microsoft.ML.Trainers.FastTree Assembly: Microsoft.ML.FastTree.dll Microsoft Documentation: Generalized Additive Model for Binary Classification

Description

Trains a gradient boosted stump per feature, on all features simultaneously, to fit target values using least-squares. It mantains no interactions between features.

Parameters

Name Short name Default Description
diskTranspose dt   Whether to utilize the disk or the data’s native transposition facilities (where applicable) when performing the transpose
enablePruning pruning True Enable post-training pruning to avoid overfitting. (a validation set is required)
entropyCoefficient e 0 The entropy (regularization) coefficient between 0 and 1
featureFlocks flocks True Whether to collectivize features during dataset preparation to speed up training
gainConfidenceLevel gainconf 0 Tree fitting gain confidence requirement (should be in the range [0,1) ).
getDerivativesSampleRate sr 1 Sample each query 1 in k times in the GetDerivatives function
learningRates lr 0.002 The learning rate
maxBins mb 255 Maximum number of distinct values (bins) per feature
maxOutput mo Upper bound on absolute value of single output
minDocuments mi 10 Minimum number of training instances required to form a partition
numIterations iter 9500 Total number of iterations over all features
numThreads t   The number of threads to use
rngSeed r1 123 The seed of the random number generator
unbalancedSets us False Should we use derivatives optimized for unbalanced sets