[Statlist] Reminder: ETH Young Data Science Researcher Seminar Zurich, Virtual Seminar Martin Wahl, HU Berlin

[Maurer Letizia]

Dear all

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

"Upper and lower bounds for the estimation of principal components"  
by Martin Wahl, HU Berlin 


Time: Friday, 20 November 2020, 15:00-​16:00
Place: Zoom at https://ethz.zoom.us/j/92367940258

Abstract: In settings where the number of observations is comparable to the dimension, principal component analysis (PCA) reveals some unexpected phenomena, ranging from eigenprojector inconsistency to eigenvalue upward bias. While such high-​dimensional phenomena are now well understood in the spiked covariance model, the goal of this talk is to discuss some extensions for the case of PCA in infinite dimensions. In particular, we will introduce a new perturbation-​theoretic framework that will allow us to characterize the behavior of eigenvalues and eigenprojectors of empirical covariance operators by the so-​called ``relative ranks''. If time permits, we will also present some corresponding minimax lower bounds for the estimation of eigenprojectors. These are obtained by a van Trees inequality for invariant statistical models.

Best wishes,

M. Azadkia, Y. Chen, M. Löffler, A. Taeb

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