Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
This story is from 2026-09-07. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2605.13612v2 Announce Type: replace-cross Abstract: Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-07 04:00 · arXiv stat.ML
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning