Neural Networks can Learn Representations with Gradient Descent

Alexandru Damian, Jason Lee, Mahdi Soltanolkotabi
Paper From BibTeX import
Proceedings of Thirty Fifth Conference on Learning Theory 178, pp. 5413–5452, 2022

Notes

Cited in riva2026task as part of the feature-learning theory we point to when sketching how SGD might reach the partitions our static theorems characterize.

References

No references yet.