[Statlist] Reminder: ETH Young Data Science Researcher Seminar Zurich, Virtual Seminar by Mohamed Ndaoud, University of Southern California, 12.06.2020

[Maurer Letizia]

Dear all

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

"Fast and adaptive iterative hard thresholding in high dimensional linear regression: A non-​convex algorithmic regularization approach"  
by Mohamed Ndaoud, University of Southern California

Time: Friday, 12.06.2020, 16:00-17:00
Place: Zoom at https://ethz.zoom.us/j/92367940258

Abstract: Datasets with large number of features are becoming increasingly available and important in every field of research and innovation, urging practitioners to develop scalable algorithms with fast convergence. The question of fast convergence in the classical problem of high dimensional linear regression has been extensively studied. Arguably, one of the fastest procedures in practice is Iterative Hard Thresholding (IHT). Still, IHT relies strongly on the knowledge of the true sparsity parameter $s$. In this paper, we present a novel fast procedure for estimation in the high dimensional linear regression model. Taking advantage of the interplay between estimation, support recovery and optimization we achieve both optimal statistical accuracy and fast convergence. The main advantage of our procedure is that it is fully adaptive, making it more practical than state of the art IHT methods. Our procedure achieves optimal statistical accuracy faster than, for instance, classical algorithms for the Lasso. As a consequence, we present a new iterative hard thresholding algorithm for high dimensional linear regression that is minimax optimal, fast and adaptive.

Best wishes,

M. Löffler, A. Taeb, Y. Chen

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