Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Enric Boix-Adsera, Etai Littwin, Emmanuel Abbe, Samy Bengio, Joshua Susskind
We identify incremental learning dynamics in transformers, where the difference between trained and initial weights progressively increases in rank. We rigorously prove this occurs under the simplifying assumptions of diagonal weight matrices and small initialization. Our experiments support the theory and also show that phenomenon can occur in practice without the simplifying assumptions.