[Statlist] ETH Young Data Science Researcher Seminar Zurich, Virtual Seminar by Arshak Minasyan, CREST-​ENSAE, Paris, 12.05.2022

[Maurer Letizia]

We are glad to announce the following talk in the virtual ETH Young Data Science Researcher Seminar Zurich

"All-​In-One Robust Estimator of the Gaussian Mean“  
by Arshak Minasyan, CREST-​ENSAE, Paris

Time: Thursday, 12 May 2022, 15.00 - 16.00
Place: Zoom at https://ethz.zoom.us/j/62895316484

Abstract: We propose a robust-​to-outliers estimator of the mean of a multivariate Gaussian distribution that enjoys the following properties: polynomial computational complexity, high breakdown point, minimax rate optimality (up to logarithmic factor) and asymptotical efficiency. Non-​asymptotic risk bound for the expected error of the proposed estimator is dimension-​free and involves only the effective rank of the covariance matrix. Moreover, we show that the obtained results can be extended to sub-​Gaussian distributions, as well as to the cases of unknown rate of contamination or unknown covariance matrix. Joint work with Arnak Dalalyan (https://arxiv.org/abs/2002.01432)


M. Azadkia, G. Chinot, J. Hörrmann, M. Löffler, A. Taeb, N. Zhivotovskiy


Seminar website: https://math.ethz.ch/sfs/news-and-events/young-data-science.html

Young Data Science Researcher Seminar Zurich – Seminar for Statistics | ETH Zurich
math.ethz.ch