${\mu}P$^2$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling$

{\mu}P$^2$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling

Sharpness Aware Minimization (SAM) enhances performance across various neural architectures and datasets. As models are continually scaled up to improve performance, a rigorous understanding of SAM's scaling behaviour is paramount. To this end, we study the infinite-width limit of neural networ...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Haas, Moritz, Xu, Jin, Cevher, Volkan, Vankadara, Leena Chennuru
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!