Gil Kur

Dr. Gil Kur is a Lecturer in the Department of Mathematics at ETH Zürich. His research focuses on statistical estimation, high-dimensional data analysis, convex regression, machine learning theory, optimization, and probability theory. He has contributed to areas such as nonparametric estimation, convex body approximation, and differential privacy mechanisms. His work bridges theoretical foundations with applications in computational statistics and optimization.

Key research themes include analyzing convergence rates of estimators, developing optimal algorithms for convex regression, and studying geometric properties of high-dimensional spaces. His recent articles explore topics like debiased LASSO methods, log-concave maximum likelihood estimation, and the performance of empirical risk minimization under various constraints.

Kur’s publications demonstrate a strong focus on rigorous mathematical analysis, often combining tools from probability, functional analysis, and convex geometry. While no specific awards or grants are listed, his active publication record reflects sustained contributions to statistical theory and machine learning fundamentals.