Scholar
Gil Kur
Google Scholar ID: yDkAhccAAAAJ
Postdoc at ETH Zürich
Citations & Impact
Citations
265
H-index
8
i10-index
7
Publications
20
Co-authors
22
list available
Publications
Resume (English only)
Academic Achievements
- Delivered several talks, including UT Austin - IFML Seminar, TTIC computer science seminar, Hausdorff Research Institute for Mathematics seminar, 2021 Annual Meeting on the Mathematical and Scientific Foundations of Deep Learning, and BIRS Geometric Nonlinear Functional Analysis workshop.
Research Experience
- Currently a postdoctoral fellow at ETH Zürich, hosted by Andreas Krause, Afonso S. Bandeira, and Fanny Yang.
Education
- PhD: EECS Department at MIT, advised by Sasha Rakhlin (in collaboration with Aditya Guntuboyina from UC Berkeley). MSc: Department of Mathematics and Computer Science at the Weizmann Institute of Science, supervised by Boaz Nadler (in collaboration with Peter J. Bickel from UC Berkeley).
Background
- Research Interests: Statistical learning theory, non-parametric and high-dimensional statistics. His theoretical work is deeply inspired by convex and high-dimensional geometry. He collaborates with practitioners to bridge theory and practice in machine learning and statistics, e.g., through test-time training and uncertainty quantification. He also works with mathematicians on problems at the intersection of the local theory of Banach spaces and statistics.
Miscellany
- Throughout his academic journey, he has been fortunate to interact with the GAFA (Geometric and Functional Analysis) community, which has shaped his understanding of high-dimensional geometry and its deep connections to statistics. He is particularly grateful to Emanuel Milman, Bo'az Klartag, Gideon Schechtman, Shiri Artstein-Avidan, Artem Zvavitch, Mark Rudelson, Alexandros Eskenazis, Grigoris Paouris, and his dear friend Dan Mikulincer for their invaluable guidance.
