Methoden vergleichen

	Robust Boosting	Boosting	Robustes Gradient Boosting
Fachgebiet	Maschinelles Lernen	Maschinelles Lernen	Maschinelles Lernen
Familie	Machine learning	Machine learning	Machine learning
Entstehungsjahr	1999–2001	1990–1997	2001
Urheber	Freund, Y.; Mason, L. et al.	Schapire, R. E.; Freund, Y.	Friedman, J. H. (with Huber loss from Huber, P. J.)
Typ	Ensemble (robust sequential boosting)	Sequential ensemble (iterative reweighting)	Ensemble (boosted trees with robust loss)
Wegweisende Quelle	Freund, Y. (2001). An adaptive version of the boost by majority algorithm. Machine Learning, 43(3), 293–318.	Freund, Y. & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.	Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232.
Aliasnamen	noise-tolerant boosting, robust AdaBoost, boosting with robust losses, outlier-resistant boosting	AdaBoost, gradient boosting, iterative reweighting ensemble, sequential ensemble	gradient boosting with Huber loss, robust GBM, outlier-robust boosting, robust gradient-boosted trees
Verwandt	6	6	6
Zusammenfassung	Robust Boosting modifies standard boosting algorithms — such as AdaBoost or gradient boosting — by replacing the default exponential or squared loss with robust loss functions (e.g., Huber, logistic, or truncated losses) or by incorporating noise-tolerance mechanisms, so that the ensemble remains accurate even when training data contain outliers, label noise, or heavy-tailed errors.	Boosting is a sequential ensemble technique that converts many simple, barely-better-than-chance learners into a single highly accurate model by repeatedly focusing training on the examples that previous learners got wrong, then combining all learners with weights proportional to their individual accuracy.	Robust Gradient Boosting is gradient boosting trained with outlier-resistant loss functions — most commonly the Huber loss or quantile (pinball) loss — instead of squared-error loss. Proposed in Friedman's seminal 2001 paper, this variant produces predictions far less distorted by extreme values or contaminated labels, while retaining the full predictive power of gradient-boosted trees.