High-dimensional asymptotics of feature learning: How one gradient step improves the representation

Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang
Paper From BibTeX import
Advances in Neural Information Processing Systems 35, pp. 37932–37946, 2022

Notes

Their high-dimensional analysis of feature learning after one gradient step is cited in riva2026task as a possible ingredient for resolving the oracle-to-trained gap.

References

No references yet.