2 papers
cs.LG2025
On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
Moritz Haas, Sebastian Bordt, Ulrike von Luxburg +1
Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models. However, it is widely believed that existing infinite-width theory…
cs.LG2024
μP: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
Moritz Haas, Jin Xu, Volkan Cevher +1
Sharpness Aware Minimization (SAM) enhances performance across various neural architectures and datasets. As models are continually scaled up to improve performance, a rigorous und…