Sara van de Geer is a mathematical statistician with main research areas empirical process theory, statistical learning theory, and nonparametric and high-dimensional statistics. She is known particularly through her books “Empirical Processes in M -estimation” (2000) and “Statistics for High-Dimensional Data”(2011, with co-author Peter Bühlmann). Sara was born and grew up in Leiden. Following a position as researcher at the Center for Mathematics and Computer Science in Amsterdam, she obtained her 1987 at the University of Leiden. She held several university positions in The Netherlands, UK and France, before joining in 2005 the Department of Mathematics at the ETH Zürich. She is past-president of the Bernoulli Society. She is a correspondent of the Dutch Royal Academy of Sciences, Knight in the Order of Orange-Nassau, Member of Leopoldina, Deutsche Akademie der Naturforscher and Member of Academia Europaea. She was invited speaker at the International Conference of Mathematicians in 2010.

Research Interests

Sara van de Geer strives in her research to formulate unifying principles for statistical theory and modelling. Her motivation lies in revealing the theoretical foundations of existing popular methods and algorithms. Typically, the models she studies are over-parametrized ones, where one needs to use regularization to avoid overfitting. After deriving entropy-based bounds for regularized estimators, she turned in 2002 to sparsity inducing regularization. Her recent work concentrates around some intertwined topics: regularization with total variation type norms, the behavior of stationary points of empirical risk functions, inference, and lower bounds. She currently is working on deriving the generalization error for interpolators and on small noise classification problems.

Membership Type

International Member

Election Year


Primary Section

Section 32: Applied Mathematical Sciences