The Drift Contract: Spectral Updates for Depth-Robust Local Learning
arXiv:2609.26811v1 Announce Type: new Abstract: Local learning trains each layer with its own auxiliary loss and no global backward pass, which makes layer updates structurally parallel. Two problems have kept it marginal: accuracy degrades as depth grows, and hyperparameters are fragile. We apply…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.LG
The Drift Contract: Spectral Updates for Depth-Robust Local Learning