[Theory] 10/16 Talks at TTIC: Gil Kur, ETH Zürich

[Mary Marre via Theory]

*When*:    Wednesday, October 16th from* 11**am - 12pm CT*

*Where*:   Talk will be given *live, in-person* at
               TTIC, 6045 S. Kenwood Avenue
               5th Floor, *Room 530*

*Virtually*: tba

*Who:  *    Gil Kur, ETH Zürich


*Title:* Minimum Norm Interpolation Meets The Local Theory of Banach Spaces

*Abstract:* Minimum-norm interpolators have recently gained attention
primarily as an analyzable model to shed light on the double descent
phenomenon observed for neural networks.  The majority of the work has
focused on analyzing interpolators in Hilbert spaces, where typically an
effectively low-rank structure of the feature covariance prevents a large
bias. More recently, tight vanishing bounds have also been shown for
isotropic high-dimensional data  for $\ell_p$-spaces with $p\in[1,2)$,
leveraging the sparse structure of the ground truth.  This work takes a
first step towards establishing a general framework that connects
generalization properties of the interpolators to well-known concepts from
high-dimensional geometry, specifically, from the local theory of Banach
spaces.

*Bio:*  Dr. Gil Kur is a postdoctoral researcher at ETH Zürich, working
under the guidance of Profs. Fanny Yang and Afonso S. Bandeira. He
completed his Ph.D. at the Massachusetts Institute of Technology, advised
by Prof. Alexander Rakhlin and Prof. Adityanand Guntuboyina (UC-Berkeley).
His research interests include statistical learning theory,
high-dimensional statistics, non-parametric statistics, empirical
processes, and convex geometry.  He is currently visiting IDEAL hosted by
Lev Reyzin at UIC.

*Host: *Avrim Blum



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL  60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20241009/b71bb6ae/attachment.html>