[Statlist] ETH Young Data Science Researcher Seminar Zurich, Virtual Seminar by Feng Ruan, UC Berkeley

[Maurer Letizia]

Dear all

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

"Searching for Interactions in Linear Time"  
by Feng Ruan, UC Berkeley

Time: Friday, 26 February 2021, 16:00-​17:00
Place: Zoom at https://ethz.zoom.us/j/92367940258

Abstract: We tackle the problem of variable selection with a focus on discovering interactions between variables. With p variables, there are O(p^k) possible interactions of order k making exhaustive search infeasible. We show that it is nonetheless possible to identify the variables involved in interactions (of any order) with only linear computation cost, O(p), and in a nonparametric fashion. Our algorithm is based on minimizing a non-​convex objective, carefully designed to have a favorable landscape. We provide finite sample guarantees on both false positives (we show all stationary points of the objective exclude noise variables) and false negatives (we characterize the sample sizes needed for gradient descent to converge to a "good’’ stationary point).

Best wishes,

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

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