Bernd Rosenow

According to our database1, Bernd Rosenow authored at least 15 papers between 2004 and 2026.

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

2026
A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification.
CoRR, May, 2026

2025
Anti-correlated noise in epoch-based stochastic gradient descent: implications for weight variances in flat directions.
Mach. Learn. Sci. Technol., 2025

Small Singular Values Matter: A Random Matrix Analysis of Transformer Models.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
Locating Information in Large Language Models via Random Matrix Theory.
CoRR, 2024

2023
Reevaluating Loss Functions: Enhancing Robustness to Label Noise in Deep Learning Models.
CoRR, 2023

Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances.
CoRR, 2023

Topological gap protocol based machine learning optimization of Majorana hybrid wires.
CoRR, 2023

Online Learning for the Random Feature Model in the Student-Teacher Framework.
CoRR, 2023

2022
Machine learning optimization of Majorana hybrid nanowires.
CoRR, 2022

Boundary between noise and information applied to filtering neural network weight matrices.
CoRR, 2022

Random matrix analysis of deep neural network weight matrices.
CoRR, 2022

2021
Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft Committee Machines.
CoRR, 2021

2004
Smooth Correlation Estimation with Application to Portfolio Credit Risk.
Proceedings of the Classification, 2004


  Loading...