MCPcopy Create free account
hub / github.com/antmachineintelligence/mtgbmcode / Shrinkage

Method Shrinkage

include/LightGBM/tree.h:149–155  ·  view source on GitHub ↗

! * \brief Shrinkage for the tree's output * shrinkage rate (a.k.a learning rate) is used to tune the training process * \param rate The factor of shrinkage */

Source from the content-addressed store, hash-verified

147 * \param rate The factor of shrinkage
148 */
149 inline void Shrinkage(double rate) {
150 #pragma omp parallel for schedule(static, 1024) if (num_leaves_ >= 2048)
151 for (int i = 0; i < num_leaves_; ++i) {
152 leaf_value_[i] *= rate;
153 }
154 shrinkage_ *= rate;
155 }
156
157 inline double shrinkage() const {
158 return shrinkage_;

Callers 6

RollbackOneIterMethod · 0.45
TrainOneIter_oldMethod · 0.45
TrainOneIter_newMethod · 0.45
RollbackOneIterMethod · 0.45
DroppingTreesMethod · 0.45
NormalizeMethod · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected