Methoden vergleichen

	Robuster Bagging	Boosting	Robust Boosting
Fachgebiet	Maschinelles Lernen	Maschinelles Lernen	Maschinelles Lernen
Familie	Machine learning	Machine learning	Machine learning
Entstehungsjahr	1996–2000s	1990–1997	1999–2001
Urheber	Breiman, L. (bagging); robust variants developed by various authors in 2000s	Schapire, R. E.; Freund, Y.	Freund, Y.; Mason, L. et al.
Typ	Ensemble (robust bootstrap aggregating)	Sequential ensemble (iterative reweighting)	Ensemble (robust sequential boosting)
Wegweisende Quelle	Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.	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.	Freund, Y. (2001). An adaptive version of the boost by majority algorithm. Machine Learning, 43(3), 293–318.
Aliasnamen	robust bootstrap aggregating, robust ensemble bagging, outlier-resistant bagging, robust BAGGing	AdaBoost, gradient boosting, iterative reweighting ensemble, sequential ensemble	noise-tolerant boosting, robust AdaBoost, boosting with robust losses, outlier-resistant boosting
Verwandt	6	6	6
Zusammenfassung	Robust Bagging extends the classic Bootstrap Aggregating (Bagging) framework by replacing or augmenting standard base learners with robust estimators — or by using robust aggregation rules — so that the ensemble remains accurate even when training data contain outliers, mislabelled instances, or heavy-tailed noise distributions.	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 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.