Rosenow, Bernd

6 publications

ICLR 2025 Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra Roman Worschech, Bernd Rosenow

AAAI 2025 Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning Max Staats, Matthias Thamm, Bernd Rosenow

NeurIPS 2025 Small Singular Values Matter: A Random Matrix Analysis of Transformer Models Max Staats, Matthias Thamm, Bernd Rosenow

ICMLW 2024 Boundary Between Noise and Information Applied to Filtering Neural Network Weight Matrices Max Staats, Matthias Thamm, Bernd Rosenow

ICMLW 2024 Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances Marcel Kühn, Bernd Rosenow

ICMLW 2024 Random Matrix Theory Analysis of Neural Network Weight Matrices Matthias Thamm, Max Staats, Bernd Rosenow