Robust Kernel Density Estimation with ...
Type de document :
Communication dans un congrès avec actes
Titre :
Robust Kernel Density Estimation with Median-of-Means principle
Auteur(s) :
Humbert, Pierre [Auteur]
Statistique mathématique et apprentissage [CELESTE]
Laboratoire de Mathématiques d'Orsay [LMO]
Le Bars, Batiste [Auteur]
Machine Learning in Information Networks [MAGNET]
Minvielle, Ludovic [Auteur]
CB - Centre Borelli - UMR 9010 [CB]
Ecole Normale Supérieure Paris-Saclay [ENS Paris Saclay]
Statistique mathématique et apprentissage [CELESTE]
Laboratoire de Mathématiques d'Orsay [LMO]
Le Bars, Batiste [Auteur]
Machine Learning in Information Networks [MAGNET]
Minvielle, Ludovic [Auteur]
CB - Centre Borelli - UMR 9010 [CB]
Ecole Normale Supérieure Paris-Saclay [ENS Paris Saclay]
Titre de la manifestation scientifique :
ICML 2022 - The 39th International Conference on Machine Learning (ICML)
Ville :
Baltimore
Pays :
Etats-Unis d'Amérique
Date de début de la manifestation scientifique :
2022-07-17
Titre de la revue :
Proceedings of Machine Learning Research
Discipline(s) HAL :
Mathématiques [math]/Statistiques [math.ST]
Statistiques [stat]/Machine Learning [stat.ML]
Statistiques [stat]/Machine Learning [stat.ML]
Résumé en anglais : [en]
In this paper, we introduce a robust nonparametric density estimator combining the popular Kernel Density Estimation method and the Median-of-Means principle (MoM-KDE). This estimator is shown to achieve robustness to any ...
Lire la suite >In this paper, we introduce a robust nonparametric density estimator combining the popular Kernel Density Estimation method and the Median-of-Means principle (MoM-KDE). This estimator is shown to achieve robustness to any kind of anomalous data, even in the case of adversarial contamination. In particular, while previous works only prove consistency results under known contamination model, this work provides finite-sample high-probability error-bounds without a priori knowledge on the outliers. Finally, when compared with other robust kernel estimators, we show that MoM-KDE achieves competitive results while having significant lower computational complexity.Lire moins >
Lire la suite >In this paper, we introduce a robust nonparametric density estimator combining the popular Kernel Density Estimation method and the Median-of-Means principle (MoM-KDE). This estimator is shown to achieve robustness to any kind of anomalous data, even in the case of adversarial contamination. In particular, while previous works only prove consistency results under known contamination model, this work provides finite-sample high-probability error-bounds without a priori knowledge on the outliers. Finally, when compared with other robust kernel estimators, we show that MoM-KDE achieves competitive results while having significant lower computational complexity.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- document
- Accès libre
- Accéder au document
- MoM_KDE_main.pdf
- Accès libre
- Accéder au document
- 2006.16590
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- MoM_KDE_main.pdf
- Accès libre
- Accéder au document