Comparer des méthodes

	SVM univarié bayésien	SVM à une classe robuste
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2001–2010	2000s–2010s
Auteur d'origine	Scholkopf et al. (base OCSVM); Bayesian extension via Tipping and others	Extensions of Scholkopf et al. (1999); robust variants developed in 2000s–2010s
Type	Probabilistic anomaly detection	Anomaly detection / novelty detection
Source fondatrice	Scholkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural Computation, 13(7), 1443–1471.	Scholkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., & Platt, J. (1999). Support vector method for novelty detection. Advances in Neural Information Processing Systems (NeurIPS), 12, 582–588.
Alias	Bayesian OCSVM, Bayesian one-class classifier, probabilistic one-class SVM, Bayes-OCSVM	Robust OCSVM, Outlier-robust One-Class SVM, Contamination-tolerant OCSVM, Robust novelty detection SVM
Apparentées	6	5
Résumé	Bayesian one-class SVM combines the classical one-class support vector machine — which learns a tight boundary around normal training examples — with Bayesian inference to produce calibrated probability estimates of anomaly, rather than only a binary flag. This allows uncertainty quantification over the novelty decision, making the approach more suitable when downstream actions depend on how confident the model is that a new observation is anomalous.	Robust One-Class SVM extends the classic One-Class Support Vector Machine for novelty and anomaly detection by incorporating robustness mechanisms — such as trimmed objectives, robust kernel choices, or contamination-tolerant loss functions — that reduce the influence of heavy-tailed noise or outliers present in the training data, yielding a decision boundary that better represents the true support of the normal class.