Bernd Rosenow

According to our database, Bernd Rosenow authored at least 12 papers between 2004 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra.

Roman Worschech, Bernd Rosenow

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning.

Max Staats, Matthias Thamm, Bernd Rosenow

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Locating Information in Large Language Models via Random Matrix Theory.

Max Staats, Matthias Thamm, Bernd Rosenow

CoRR, 2024

2023

Reevaluating Loss Functions: Enhancing Robustness to Label Noise in Deep Learning Models.

Max Staats, Matthias Thamm, Bernd Rosenow

CoRR, 2023

Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances.

Marcel Kühn, Bernd Rosenow

CoRR, 2023

Topological gap protocol based machine learning optimization of Majorana hybrid wires.

Matthias Thamm, Bernd Rosenow

CoRR, 2023

Online Learning for the Random Feature Model in the Student-Teacher Framework.

Roman Worschech, Bernd Rosenow

CoRR, 2023

2022

Machine learning optimization of Majorana hybrid nanowires.

Matthias Thamm, Bernd Rosenow

CoRR, 2022

Boundary between noise and information applied to filtering neural network weight matrices.

Max Staats, Matthias Thamm, Bernd Rosenow

CoRR, 2022

Random matrix analysis of deep neural network weight matrices.

Matthias Thamm, Max Staats, Bernd Rosenow

CoRR, 2022

2021

Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft Committee Machines.

Frederieke Richert, Roman Worschech, Bernd Rosenow

CoRR, 2021

2004

Smooth Correlation Estimation with Application to Portfolio Credit Risk.

Rafael Weißbach, Bernd Rosenow

Proceedings of the Classification, 2004