Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| XGBoost Robuste× | LightGBM Robuste× | |
|---|---|---|
| Domaine | Apprentissage automatique | Apprentissage automatique |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2016 (XGBoost); robust loss concept from 1964 | 2017 (LightGBM); robust variants widely adopted 2018–present |
| Auteur d'origine≠ | Chen, T. & Guestrin, C. (XGBoost); Huber, P. J. (robust loss) | Ke, G. et al. (LightGBM); robust objectives adapted from Friedman, J. H. |
| Type≠ | Ensemble (gradient boosting with robust objective) | Ensemble (gradient boosted decision trees with robust loss) |
| Source fondatrice≠ | Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. DOI ↗ | Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Advances in Neural Information Processing Systems, 30, 3146–3154. link ↗ |
| Alias | XGBoost with Huber loss, outlier-robust gradient boosting, robust GBDT, XGBoost robust regression | Robust LGBM, LightGBM with Huber loss, outlier-resistant gradient boosting, robust gradient boosted trees |
| Apparentées | 6 | 6 |
| Résumé≠ | Robust XGBoost combines the scalable gradient boosting framework of XGBoost with robust loss functions — primarily the Huber loss or its variants — to produce a gradient boosted tree ensemble that resists the distorting influence of outliers. By replacing the squared-error objective with a loss that down-weights large residuals, the model delivers reliable predictions on continuous targets even when training data contain extreme values or label noise. | Robust LightGBM is a gradient boosting framework that pairs Microsoft's highly efficient LightGBM engine with outlier-resistant loss functions — most commonly Huber, quantile, or mean absolute error — so that predictions are not unduly distorted by extreme or erroneous observations. It retains LightGBM's speed and leaf-wise tree growth while providing resistance to heavy-tailed noise in the target variable. |
| ScholarGateJeu de données ↗ |
|
|