Focus and Dilution: The Multi-stage Learning Process of Attention

May 02, 2026 ยท Grace Period ยท ๐Ÿ› ICML 2026 spotlight

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Zheng-An Chen, Pengxiao Lin, Zhi-Qin John Xu, Tao Luo arXiv ID 2605.01199 Category cs.LG: Machine Learning Citations 0 Venue ICML 2026 spotlight
Abstract
Transformer-based models have achieved remarkable success across a wide range of domains, yet our understanding of their training dynamics remains limited. In this work, we identify a recurrent focus-dilution cycle in attention learning and provide a rigorous explanation in a one-layer Transformer setting for Markovian data via gradient-flow analysis. Using stage-wise linearization around critical points, we show that a single focus-dilution cycle can be decomposed into a sequence of distinct stages. First, embedding and projection rapidly condense to a rank-one structure, while attention parameters remain effectively frozen. Then, the attention parameters begin to increase, inducing a frequency-driven focus toward high-frequency tokens. As attention continues to evolve, it generates next-order perturbations in embeddings, leading to a mass-redistribution mechanism that progressively dilutes this focus. Finally, small asymmetries among low-frequency tokens lift a degenerate critical point, opening new embedding directions and initiating the next cycle. Experiments on synthetic Markovian data as well as WikiText and TinyStories corroborate the predicted stages and cyclical dynamics.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning