"non-linear functions" Papers
2 papers found
Conference
Asymptotics of feature learning in two-layer networks after one gradient-step
Hugo Cui, Luca Pesce, Yatin Dandi et al.
ICML 2024spotlightarXiv:2402.04980
26
citations
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
Xiang Cheng, Yuxin Chen, Suvrit Sra
ICML 2024arXiv:2312.06528
63
citations