Search Results for author: Guillaume Lecue

Found 1 papers, 0 papers with code

MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means

no code implementations13 Feb 2018 Matthieu Lerasle, Zoltan Szabo, Timothee Mathieu, Guillaume Lecue

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.