Enregistré dans:
Détails bibliographiques
Auteurs principaux: Karagodin, Nikita, Ge, Shu, Polyanskiy, Yury, Rigollet, Philippe
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.22026
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • We study the effect of normalization schemes on token representations in deep transformers. Modeling their evolution as interacting particles on the sphere, we show that normalization acts as a form of speed regulation. This perspective enables a unified analysis of several schemes -- including Post-LN, Pre-LN, Mix-LN, Peri-LN, nGPT -- revealing how they influence clustering dynamics and representation collapse. Our framework clarifies how different schemes shape token representations across layers and provides a principled basis for comparing them, identifying Peri-LN as a particularly effective choice.