[Statlist] ETH Young Data Science Researcher Seminar Zurich, Virtual Seminar by Morgane Austern, Microsoft Research New England

Maurer Letizia |et|z|@m@urer @end|ng |rom ethz@ch
Wed May 26 13:29:11 CEST 2021


Dear all

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

"Asymptotics of learning on dependent and structured random objects“  
by Morgane Austern, Microsoft Research New England

Time: Friday, 28 May 2021, 15.00 - 16.00
Place: Zoom at  https://ethz.zoom.us/j/97914933906

Abstract: Classical statistical inference relies on numerous tools from probability theory to study the properties of estimators. However, these same tools are often inadequate to study modern machine problems that frequently involve structured data (e.g networks) or complicated dependence structures (e.g dependent random matrices). In this talk, we extend universal limit theorems beyond the classical setting. Firstly, we consider distributionally \structured" and dependent random object {i.e random objects whose distribution are invariant under the action of an amenable group. We show, under mild moment and mixing conditions, a series of universal second and third order limit theorems: central-limit theorems, concentration inequalities, Wigner semi-circular law and Berry-Esseen bounds. The utility of these will be illustrated by a series of examples in machine learning, network and information theory. Secondly by building on these results, we establish the asymptotic distribution of the cross-validated risk with the number of folds allowed to grow at an arbitrary rate. Using this, we study the statistical speed-up of cross validation compared to a train-test split procedure, which reveals surprising results even when used on simple estimators.

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

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


More information about the Statlist mailing list