Florian Rossmannek

Nanyang Technological University — Singapore

Computer Science · Physical Sciences

5h-index116citations13works0.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Neural Networks and Applications(5), Stochastic Gradient Optimization Techniques(5), Sparse and Compressive Sensing Techniques(3), Machine Learning and ELM(3), Model Reduction and Neural Networks(2)

Publications13 total

Stochastic dynamics learning with state-space systems
arXiv (Cornell University)·2025Open Access
Fading Memory and the Convolution Theorem
IEEE Transactions on Automatic Control·2025
State-space systems as dynamic generative models
Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences·2025· 1 cited
Gradient Descent Provably Escapes Saddle Points in the Training of Shallow ReLU Networks
Journal of Optimization Theory and Applications·2024· 1 citedOpen Access
Fading memory and the convolution theorem
arXiv (Cornell University)·2024Open Access
State-space systems as dynamic generative models
arXiv (Cornell University)·2024Open Access
Efficient Sobolev approximation of linear parabolic PDEs in high dimensions
arXiv (Cornell University)·2023Open Access
Gradient descent provably escapes saddle points in the training of shallow ReLU networks
arXiv (Cornell University)·2022· 1 citedOpen Access
Landscape Analysis for Shallow Neural Networks: Complete Classification of Critical Points for Affine Target Functions
Journal of Nonlinear Science·2022· 10 citedOpen Access
A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions
Journal of Complexity·2022· 24 citedOpen Access
Non-convergence of stochastic gradient descent in the training of deep neural networks
Repository for Publications and Research Data (ETH Zurich)·2021· 37 citedOpen Access
Landscape analysis for shallow ReLU neural networks: complete classification of critical points for affine target functions.
arXiv (Cornell University)·2021· 11 citedOpen Access
Efficient Approximation of High-Dimensional Functions With Neural Networks
IEEE Transactions on Neural Networks and Learning Systems·2021· 31 citedOpen Access

Frequent Co-authors

Patrick Cheridito(8), Arnulf Jentzen(7), Juan‐Pablo Ortega(5), Adrian Riekert(1)