832 citations · 3k across the 34 of their papers we have counts for
32 papers · 1 filter
Entropy bounds for the absolute convex hull of tensors
Sara van de Geer
We derive entropy bounds for the absolute convex hull of vectors in and apply this to the case where is the…
Finite sample rates for logistic regression with small noise or few samples
Felix Kuchelmeister, Sara van de Geer
The logistic regression estimator is known to inflate the magnitude of its coefficients if the sample size is small, the dimension is (moderately) large or the signal-to-no…
AdaBoost and robust one-bit compressed sensing
Geoffrey Chinot, Felix Kuchelmeister, Matthias Löffler +1
This paper studies binary classification in robust one-bit compressed sensing with adversarial errors. It is assumed that the model is overparameterized and that the parameter of i…
On the efficiency of the de-biased Lasso
Sara van de Geer
We consider the high-dimensional linear regression model with Gaussian noise and Gaussian random design . We assume that is non-singular an…
Asymptotic Confidence Regions for High-dimensional Structured Sparsity
Benjamin Stucky, Sara van de Geer
In the setting of high-dimensional linear regression models, we propose two frameworks for constructing pointwise and group confidence sets for penalized estimators which incorpora…
Some exercises with the Lasso and its compatibility constant
Sara van de Geer
We consider the Lasso for a noiseless experiment where one has observations and uses the penalized version of basis pursuit. We compute for some special designs the compati…
Robust Low-Rank Matrix Estimation
Andreas Elsener, Sara van de Geer
Many results have been proved for various nuclear norm penalized estimators of the uniform sampling matrix completion problem. However, most of these estimators are not robust: in…
On concentration for (regularized) empirical risk minimization
Sara van de Geer, Martin Wainwright
Rates of convergence for empirical risk minimizers have been well studied in the literature. In this paper, we aim to provide a complementary set of results, in particular by showi…
Semi-parametric efficiency bounds for high-dimensional models
Jana Jankova, Sara van de Geer
Asymptotic lower bounds for estimation play a fundamental role in assessing the quality of statistical procedures. In this paper we propose a framework for obtaining semi-parametri…
Concentration behavior of the penalized least squares estimator
Alan Muro, Sara van de Geer
Consider the standard nonparametric regression model and take as estimator the penalized least squares function. In this article, we study the trade-off between closeness to the tr…
Sharp Oracle Inequalities for Square Root Regularization
Benjamin Stucky, Sara van de Geer
We study a set of regularization methods for high-dimensional linear regression models. These penalized estimators have the square root of the residual sum of squared errors as los…
Honest confidence regions and optimality in high-dimensional precision matrix estimation
Jana Janková, Sara van de Geer
We propose methodology for estimation of sparse precision matrices and statistical inference for their low-dimensional parameters in a high-dimensional setting where the number of…
-confidence sets in high-dimensional regression
Sara van de Geer, Benjamin Stucky
We study a high-dimensional regression model. Aim is to construct a confidence set for a given group of regression coefficients, treating all other regression coefficients as nuisa…
Statistical Theory for High-Dimensional Models
Sara van de Geer
These lecture notes consist of three chapters. In the first chapter we present oracle inequalities for the prediction error of the Lasso and square-root Lasso and briefly describe…
Discussion: "A significance test for the lasso"
Peter Bühlmann, Lukas Meier, Sara van de Geer
Discussion of "A significance test for the lasso" by Richard Lockhart, Jonathan Taylor, Ryan J. Tibshirani, Robert Tibshirani [arXiv:1301.7161].
The additive model with different smoothness for the components
Sara van de Geer, Alan Muro
We consider an additive regression model consisting of two components and , where the first component is in some sense "smoother" than the second . Smoothness…
Censored linear model in high dimensions
Patric Müller, Sara van de Geer
Censored data are quite common in statistics and have been studied in depth in the last years. In this paper we consider censored high-dimensional data. High-dimensional models are…
On higher order isotropy conditions and lower bounds for sparse quadratic forms
Sara van de Geer, Alan Muro
This study aims at contributing to lower bounds for empirical compatibility constants or empirical restricted eigenvalues. This is of importance in compressed sensing and theory fo…
Worst possible sub-directions in high-dimensional models
Sara van de Geer
We examine the rate of convergence of the Lasso estimator of lower dimensional components of the high-dimensional parameter. Under bounds on the -norm on the worst possible…
Confidence intervals for high-dimensional inverse covariance estimation
Jana Jankova, Sara van de Geer
We propose methodology for statistical inference for low-dimensional parameters of sparse precision matrices in a high-dimensional setting. Our method leads to a non-sparse estimat…
On the uniform convergence of empirical norms and inner products, with application to causal inference
Sara van de Geer
Uniform convergence of empirical norms - empirical measures of squared functions - is a topic which has received considerable attention in the literature on empirical processes. Th…
The partial linear model in high dimensions
Patric Müller, Sara van de Geer
Partial linear models have been widely used as flexible method for modelling linear components in conjunction with non-parametric ones. Despite the presence of the non-parametric p…
On asymptotically optimal confidence regions and tests for high-dimensional models
Sara van de Geer, Peter Bühlmann, Ya'acov Ritov +1
We propose a general method for constructing confidence intervals and statistical tests for single or low-dimensional components of a large parameter vector in a high-dimensional m…
Confidence sets in sparse regression
Richard Nickl, Sara van de Geer
The problem of constructing confidence sets in the high-dimensional linear model with response variables and parameters, possibly , is considered. Full honest adapt…