5 papers
Noisy nonlinear information and entropy numbers
David Krieg, Erich Novak, Leszek Plaskota +1
It is impossible to recover a vector from with less than linear measurements, even if the measurements are chosen adaptively. Recently, it has been shown that on…
Sampling and entropy numbers in the uniform norm
Mario Ullrich
We prove a sharp bound between sampling numbers and entropy numbers in the uniform norm for bounded convex sets of bounded functions.
Sparse grids vs. random points for high-dimensional polynomial approximation
Jakob Eggl, Elias Mindlberger, Mario Ullrich
We study polynomial approximation on a -cube, where is large, and compare interpolation on sparse grids, aka Smolyak's algorithm (SA), with a simple least squares method bas…
Nonlocal techniques for the analysis of deep ReLU neural network approximations
Cornelia Schneider, Mario Ullrich, Jan Vybiral
Recently, Daubechies, DeVore, Foucart, Hanin, and Petrova introduced a system of piece-wise linear functions, which can be easily reproduced by artificial neural networks with the…
How many continuous measurements are needed to learn a vector?
David Krieg, Erich Novak, Mario Ullrich
One can recover vectors from with arbitrary precision, using only continuous measurements that are chosen adaptively. This surprising r…