1. A machine learning technique that builds an ensemble of weak predictive models (typically decision trees) sequentially, where each new model corrects the errors made by the previous ones by fitting to the residuals
Gradient boosting is widely used in competition machine learning for its high predictive accuracy.
O aumento de gradiente é amplamente utilizado em competições de aprendizado de máquina pela sua alta precisão preditiva.
2. An iterative method that optimizes a loss function by adding weak learners that move in the direction of the negative gradient
We used gradient boosting to improve our model's performance on the test dataset.
Utilizamos aumento de gradiente para melhorar o desempenho do nosso modelo no conjunto de dados de teste.