Mean embeddings provide an extremely flexible and powerful tool in machine learning and statistics to represent probability distributions and define a semi-metric (MMD, maximum mean discrepancy; also called N-distance or energy distance), with numerous successful applications. The representation is constructed as the expectation of the feature map defined by a kernel. As a mean, its classical empirical estimator, however, can be arbitrary severely affected even by a single outlier in case of unbounded features. To the best of our knowledge, unfortunately even the consistency of the existing few techniques trying to alleviate this serious sensitivity bottleneck is unknown. In this paper, we show how the recently emerged principle of median-of-means can be used to design estimators for kernel mean embedding and MMD with excessive resistance properties to outliers, and optimal sub-Gaussian deviation bounds under mild assumptions.
Matthieu Lerasle (Laboratoire de Mathématiques d'Orsay, Univ. Paris-Sud; CNRS, Université Paris Saclay, France)
Zoltan Szabo (Ecole Polytechnique)
Timothée Mathieu (Laboratoire de Mathématiques d'Orsay, Univ. Paris-Sud, France)
Guillaume Lecue (CREST)
Related Events (a corresponding poster, oral, or spotlight)
2019 Poster: MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means »
Thu Jun 13th 01:30 -- 04:00 AM Room Pacific Ballroom