1 code implementation • 5 May 2021 • Geoffrey Chinot, Felix Kuchelmeister, Matthias Löffler, Sara van de Geer
This paper studies binary classification in robust one-bit compressed sensing with adversarial errors.
no code implementations • 1 Dec 2020 • Geoffrey Chinot, Matthias Löffler, Sara van de Geer
This article develops a general theory for minimum norm interpolating estimators and regularized empirical risk minimizers (RERM) in linear models in the presence of additive, potentially adversarial, errors.
1 code implementation • 27 Nov 2020 • Peter Hinz, Sara van de Geer
Feed-forward ReLU neural networks partition their input domain into finitely many "affine regions" of constant neuron activation pattern and affine behaviour.
Optimization and Control
no code implementations • 17 Nov 2019 • Francesco Ortelli, Sara van de Geer
We study the theoretical properties of image denoising via total variation penalized least-squares.
no code implementations • 24 Apr 2019 • Francesco Ortelli, Sara van de Geer
We establish adaptive results for trend filtering: least squares estimation with a penalty on the total variation of $(k-1)^{\rm th}$ order differences.
no code implementations • 28 Feb 2019 • Francesco Ortelli, Sara van de Geer
Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017).
no code implementations • 5 Jun 2018 • Peter Hinz, Sara van de Geer
More precisely, the information about the number regions per dimensionality is pushed through the layers starting with one region of the input dimension of the neural network and using a recursion based on an analysis of how many regions per output dimensionality a subsequent layer with a certain width can induce on an input region with a given dimensionality.
no code implementations • 4 Jun 2018 • Francesco Ortelli, Sara van de Geer
We generalize to tree graphs obtained by connecting path graphs an oracle result obtained for the Fused Lasso over the path graph.
no code implementations • 28 Jun 2017 • 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 incorporate prior knowledge about the organization of the non-zero coefficients.