Statistics and Machine Learning
Projection Pursuit in High Dimensions
Peter J. Bickel, Gil Kur* and Boaz Nadler (alphabetical)
Proceedings of the National Academy of Sciences
Space Lower Bounds for Linear Prediction
Yuval Dagan*, Gil Kur, and Ohad Shamir
Conference on Learning Theory 2019
Convex Regression in Multidimensions: Suboptimality of Least Squares Estimators
Gil Kur*, Fuchang Gao, Adityanand Guntuboyina, and Bodhi Sen
Annals of Statistics
On Suboptimality of Least Squares with Application to Estimation of Convex Bodies
Gil Kur*, Adityanand Guntuboyina, and Alexander Rakhlin
Conference on Learning Theory 2020
On the Minimal Error of Empirical Risk Minimization
Gil Kur* and Alexander Rakhlin
Conference on Learning Theory 2021
Video
A Bounded-Noise Mechanism for Differential Privacy
Yuval Dagan* and Gil Kur
Conference on Learning Theory 2022
An Efficient Minimax Optimal Estimator for Multivariate Convex Regression
Gil Kur* and Eli Putterman
Conference on Learning Theory 2022
Slides (on estimating a norm of a convex function via a ``smart'' averaging)
Tyler's and Maronna's M-estimators: Non-Asymptotic Concentration Results
Elad Romanov*, Gil Kur, and Boaz Nadler
Journal of Multivariate Analysis
On the Variance, Admissibility, and Stability of Empirical Risk Minimization
Gil Kur*, Eli Putterman, and Alexander Rakhlin
Neurips 2023 (spotlight)
Video (presented by Eli Putterman)
Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of 2-Uniform Convexity
Gil Kur* and Pierre Bizeul
Video
Submitted
Preliminary work: Minimum Norm Interpolation Meets The Local Theory of Banach Spaces
Gil Kur* and Pedro Abdalla, Pierre Bizeul, and Fanny Yang
International Conference on Machine Learning 2024
Debiased LASSO under Poisson-Gauss Model
Pedro Abdalla* and Gil Kur (alphabetical)
Information and Inference: A Journal of the IMA
Revisiting Knowledge Distillation: surprising gains in data efficiency
Giulia Lanzillotta*, Felix Sarnthein, Gil Kur, Thomas Hofmann, and Bobby He**
NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning
Convergence rates for estimating multivariate scale mixtures of uniform densities
Arlene KH Kim*, Gil Kur, and Adityanand Guntuboyina
Electronic Journal of Statistics
Adaptive Convergence Rates for Log-Concave Maximum Likelihood
Gil Kur* and Adityanand Guntuboyina
AISTATS 2025
Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
Jonas Hübotter*, Patrick Wolf*, Alexander Shevchenko*, Dennis Jüni, Andreas Krause, and Gil Kur**
Oral at NeurIPS 2025 CCFM Workshop
ICLR 2026
Early-Stopping in Linear Least Squares over Convex Bodies
Tobias Wegel*, Gil Kur, and Patrick Rebeschini
AISTATS 2026
Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of Gaussianity
Gil Kur* and Reese Pathak
A New Perspective on Least-Norm Interpolation Under Gaussian Covariates
Gil Kur*, Zong Shang, Paul Simanjuntak, Guillaume Lecue, and Reese Pathak**
AISTATS 2026
Local Sparsity Enables Unsupervised LLM Safety Detection
Xin Chen*, Gil Kur**, Alexander Shevchenko**, and Andreas Krause
NeurIPS 2026
Random Polytopes and Convex Geometry
Approximation of the Euclidean ball by polytopes with a restricted number of facets
Gil Kur
Studia Mathematica
A Concentration Inequality for Random Polytopes, Dirichlet-Voronoi Tiling Numbers and the Geometric Balls and Bins Problem
Steven Hoehner and Gil Kur* (alphabetical)
Discrete & Computational Geometry
Intrinsic and dual volume deviations of convex bodies and polytopes
Florian Besau, Steven Hoehner*, and Gil Kur (alphabetical)
International Mathematical Research Notes
Slides (by Steven Hoehner)
On the Optimality of Random Partial Sphere Coverings in High Dimensions
Steven Hoehner and Gil Kur (alphabetical, equal contributions) --- special acknowledgment to Emanuel Milman
Proceedings of the American Mathematical Society
Preprints
Optimality of Maximum Likelihood for Log-Concave Density Estimation and Convex Regression
Gil Kur*, Yuval Dagan, and Alexander Rakhlin
Grokking through the Lens of Minimum-Norm Interpolation
Gil Kur*, Ileana Rugina, Clémentine CJ Dominé, and Marco Mondelli*
In Preparation
New Perspectives on Self Distaltion: From Theory to Practice
Daniel Marta*, Gil Kur*, Alexander Shevchenko*, Marco Mondelli** and Andreas Krause**
On a Quantitative Anderson's Theorem
Pierre Bizeul, Alexandros Eskenazis, and Gil Kur (alphabetical, equal contribution)
On a Quantitative Version of Anderson’s Theorem in Gauss Space
Gil Kur, Grigoris Paouris, and Reese Pathak (alphabetical, equal contribution)
Survey: Studying Minimum-Norm Interpolation via the Local Theory of Banach Spaces
(Based on my few works on minimum norm interpolation and many other insights)