Felix Voigtlaender
Felix Voigtlaender
Catholic University Eichstätt-Ingolstadt
Bestätigte E-Mail-Adresse bei - Startseite
Zitiert von
Zitiert von
Optimal approximation of piecewise smooth functions using deep ReLU neural networks
P Petersen, F Voigtlaender
Neural Networks 108, 296-330, 2018
Approximation spaces of deep neural networks
R Gribonval, G Kutyniok, M Nielsen, F Voigtlaender
Constructive Approximation 55 (1), 259-367, 2022
Topological properties of the set of functions generated by neural networks of fixed size
P Petersen, M Raslan, F Voigtlaender
Foundations of Computational Mathematics 21, 375-444, 2021
Identifying the root causes of wait states in large-scale parallel applications
D Böhme, M Geimer, L Arnold, F Voigtlaender, F Wolf
ACM Transactions on Parallel Computing (TOPC) 3 (2), 1-24, 2016
Equivalence of approximation by convolutional neural networks and fully-connected networks
P Petersen, F Voigtlaender
Proceedings of the American Mathematical Society 148 (4), 1567-1581, 2020
The universal approximation theorem for complex-valued neural networks
F Voigtlaender
Applied and Computational Harmonic Analysis 64, 33-61, 2023
Embedding theorems for decomposition spaces with applications to wavelet coorbit spaces
F Voigtlaender
Dissertation, Aachen, Techn. Hochsch., 2015, 2016
Wavelet coorbit spaces viewed as decomposition spaces
H Führ, F Voigtlaender
Journal of Functional Analysis 269 (1), 80-154, 2015
Neural network approximation and estimation of classifiers with classification boundary in a Barron class
A Caragea, P Petersen, F Voigtlaender
The Annals of Applied Probability 33 (4), 3039-3079, 2023
Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces
P Grohs, F Voigtlaender
Foundations of Computational Mathematics, 1-59, 2023
Embeddings of decomposition spaces
F Voigtlaender
American Mathematical Society 287 (1426), 2023
Resolution of the wavefront set using general continuous wavelet transforms
J Fell, H Führ, F Voigtlaender
Journal of Fourier Analysis and Applications 22 (5), 997-1058, 2016
Sampling numbers of smoothness classes via ℓ1-minimization
T Jahn, T Ullrich, F Voigtlaender
Journal of Complexity 79, 101786, 2023
Approximation in Lp(µ) with deep ReLU neural networks
F Voigtlaender, P Petersen
2019 13th International conference on Sampling Theory and Applications …, 2019
On dual molecules and convolution-dominated operators
JL Romero, JT van Velthoven, F Voigtlaender
Journal of Functional Analysis 280 (10), 108963, 2021
Negative results for approximation using single layer and multilayer feedforward neural networks
JM Almira, PE Lopez-de-Teruel, DJ Romero-López, F Voigtlaender
Journal of mathematical analysis and applications 494 (1), 124584, 2021
Optimal learning of high-dimensional classification problems using deep neural networks
P Petersen, F Voigtlaender
arXiv preprint arXiv:2112.12555, 2021
Design and properties of wave packet smoothness spaces
D Bytchenkoff, F Voigtlaender
Journal de Mathématiques Pures et Appliquées 133, 185-262, 2020
Quantitative approximation results for complex-valued neural networks
A Caragea, DG Lee, J Maly, G Pfander, F Voigtlaender
SIAM Journal on Mathematics of Data Science 4 (2), 553-580, 2022
Guided performance analysis combining profile and trace tools
J Giménez, J Labarta, FX Pegenaute, HF Wen, D Klepacki, IH Chung, ...
European Conference on Parallel Processing, 513-521, 2010
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20