Gil Kur

I am a postdoctoral fellow at ETH Zürich, hosted by Andreas Krause, Fanny Yang, and Afonso S. Bandeira. Before this, I completed my Ph.D. in the EECS Department at MIT, where I was very fortunate to be advised by Sasha Rakhlin in collaboration with Aditya Guntuboyina (UC Berkeley). I earned my master’s degree from the Department of Mathematics and Computer Science at the Weizmann Institute of Science, under the excellent supervision of Boaz Nadler in collaboration with Peter J. Bickel (UC Berkeley).

Email:
{firstname}.{surname}@inf.ethz.ch

Research Interests: Statistical learning theory, non-parametric and high-dimensional statistics.
My theoretical work is deeply inspired by and builds upon convex and high-dimensional geometry (also known as finite-dimensional Banach space theory).

In addition, I am interested in the practical implications of theory in applied machine learning and statistics, for example, test time tuning and uncertainty quantification.

Recorded Talks:

UT Austin - IFML Seminar - Spring 25'- Video
TTIC - computer science seminar - Fall ‘25 - Video
Hausdorff Research Institute for Mathematics - Spring 24’- Video
2021 Annual Meeting on the Mathematical and Scientific Foundations of Deep Learning - Video
BIRS - Geometric Nonlinear Functional Analysis workshop - Video

*Acknowledgment:

Throughout my academic journey, from my undergraduate studies to the present, I have been fortunate to interact with the GAFA (Geometric and Functional Analysis) community, which has shaped my understanding of high-dimensional geometry and its deep connections to statistics. In particular, I am deeply grateful to Emanuel Milman, Bo’az Klartag, Gideon Schechtman, Shiri Artstein-Avidan, Artem Zvavitch, Mark Rudelson, Alexandros Eskenazis, and Grigoris Paouris. Your guidance has been invaluable!.