Florian Rossmannek

J. Optim. Theory Appl., December, 2024

Fading memory and the convolution theorem.

[BibT_eX]

[DOI]

Juan-Pablo Ortega

CoRR, 2024

State-Space Systems as Dynamic Generative Models.

[BibT_eX]

[DOI]

Juan-Pablo Ortega

CoRR, 2024

2023

The curse of dimensionality and gradient-based training of neural networks: shrinking the gap between theory and applications.

[BibT_eX]

[DOI]

PhD thesis, 2023

Efficient Sobolev approximation of linear parabolic PDEs in high dimensions.

[BibT_eX]

[DOI]

CoRR, 2023

2022

Efficient Approximation of High-Dimensional Functions With Neural Networks.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2022

Landscape Analysis for Shallow Neural Networks: Complete Classification of Critical Points for Affine Target Functions.

[BibT_eX]

[DOI]

J. Nonlinear Sci., 2022

A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions.

[BibT_eX]

[DOI]

J. Complex., 2022

2021

Non-convergence of stochastic gradient descent in the training of deep neural networks.

[BibT_eX]

[DOI]

J. Complex., 2021

Landscape analysis for shallow ReLU neural networks: complete classification of critical points for affine target functions.

[BibT_eX]

[DOI]

CoRR, 2021

2019

Efficient approximation of high-dimensional functions with deep neural networks.

[BibT_eX]

[DOI]