Florian Rossmannek

Orcid: 0000-0001-5772-5086

According to our database1, Florian Rossmannek authored at least 9 papers between 2019 and 2023.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
The curse of dimensionality and gradient-based training of neural networks: shrinking the gap between theory and applications.
PhD thesis, 2023

Efficient Sobolev approximation of linear parabolic PDEs in high dimensions.
CoRR, 2023

2022
Efficient Approximation of High-Dimensional Functions With Neural Networks.
IEEE Trans. Neural Networks Learn. Syst., 2022

Landscape Analysis for Shallow Neural Networks: Complete Classification of Critical Points for Affine Target Functions.
J. Nonlinear Sci., 2022

A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions.
J. Complex., 2022

Gradient descent provably escapes saddle points in the training of shallow ReLU networks.
CoRR, 2022

2021
Non-convergence of stochastic gradient descent in the training of deep neural networks.
J. Complex., 2021

Landscape analysis for shallow ReLU neural networks: complete classification of critical points for affine target functions.
CoRR, 2021

2019
Efficient approximation of high-dimensional functions with deep neural networks.
CoRR, 2019


  Loading...