activity
20142022
most citedOptimal learning of high-dimensional classification problems using deep neural networks

4 citations · 10 across the 5 of their papers we have counts for

collaborators

5 papers

math.NA2022★ 4 cited

Sampling numbers of smoothness classes via -minimization

Thomas Jahn, Tino Ullrich, Felix Voigtlaender

Using techniques developed recently in the field of compressed sensing we prove new upper bounds for general (nonlinear) sampling numbers of (quasi-)Banach smoothness spaces in $L^…

math.FA2022

sampling numbers for the Fourier-analytic Barron space

Felix Voigtlaender

In this paper, we consider Barron functions of smoothness , which are functions that can be written as \[ f(x) = \int_{\mathbb{R}^d} F(ξ) \, e^{2…

math.FA2021★ 4 cited

Optimal learning of high-dimensional classification problems using deep neural networks

Philipp Petersen, Felix Voigtlaender

We study the problem of learning classification functions from noiseless training samples, under the assumption that the decision boundary is of a certain regularity. We establish…

math.FA2016★ 2 cited

Structured, compactly supported Banach frame decompositions of decomposition spaces

Felix Voigtlaender

$\newcommand{mc}[1]{\mathcal{#1}}$ $\newcommand{D}{\mc{D}(\mc{Q},L^p,\ell_w^q)}$ We present a framework for the construction of structured, possibly compactly supported Banach fram…

math.FA2014

Resolution of the wavefront set using general continuous wavelet transforms

Jonathan Fell, Hartmut Führ, Felix Voigtlaender

We consider the problem of characterizing the wavefront set of a tempered distribution in terms of its continuous wavelet transform, where the la…