[Submitted on 1 Dec 2025 (v1), last revised 30 Jan 2026 (this version, v4)] · arXiv.org

View PDF HTML (experimental)

Abstract:We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein gradient flows, synchronization models (Kuramoto), and mean-shift clustering. Central to our results is a global clustering phenomenon whereby tokens cluster asymptotically after long metastable states where they are arranged into multiple clusters. We further analyze a tractable equiangular reduction to obtain exact clustering rates, show how commonly used normalization schemes alter contraction speeds, and identify a phase transition for long-context attention. The results highlight both the mechanisms that drive representation collapse and the regimes that preserve expressive, multi-cluster structure in deep attention architectures.
Comments: to appear as Proceedings of the ICM2026, Philadelphia, USA
Subjects: Machine Learning (cs.LG); Mathematical Physics (math-ph); Dynamical Systems (math.DS); Probability (math.PR)
Cite as: arXiv:2512.01868 [cs.LG]
  (or arXiv:2512.01868v4 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2512.01868

arXiv-issued DOI via DataCite

Submission history

From: Philippe Rigollet [view email]
[v1] Mon, 1 Dec 2025 16:51:00 UTC (539 KB)
[v2] Tue, 9 Dec 2025 14:40:27 UTC (539 KB)
[v3] Wed, 7 Jan 2026 15:27:09 UTC (539 KB)
[v4] Fri, 30 Jan 2026 18:12:44 UTC (539 KB)

Read the original on arxiv.org ↗