Linear attention is (maybe) all you need (to understand Transformer optimization)

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 67
  • Download : 0
Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics. We make progress towards understanding the subtleties of training Transformers by carefully studying a simple yet canonical linearized shallow Transformer model. Specifically, we train linear Transformers to solve regression tasks, inspired by J. von Oswald et al. (ICML 2023), and K. Ahn et al. (NeurIPS 2023). Most importantly, we observe that our proposed linearized models can reproduce several prominent aspects of Transformer training dynamics. Consequently, the results obtained in this paper suggest that a simple linearized Transformer model could actually be a valuable, realistic abstraction for understanding Transformer optimization.
International Conference on Learning Representations (ICLR)
Issue Date

12th International Conference on Learning Representations, ICLR 2024

Appears in Collection
AI-Conference Papers(학술대회논문)
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0