English

Normalization in Attention Dynamics

Machine Learning 2025-11-12 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2510.22026,
  title  = {Normalization in Attention Dynamics},
  author = {Nikita Karagodin and Shu Ge and Yury Polyanskiy and Philippe Rigollet},
  journal= {arXiv preprint arXiv:2510.22026},
  year   = {2025}
}

Comments

39th Conference on Neural Information Processing Systems (NeurIPS 2025), 23 pages

R2 v1 2026-07-01T07:05:02.850Z