Width and Depth Limits Commute During Training
arXiv:2610.30729v1 Announce Type: cross Abstract: Recent work established that the infinite-width and infinite-depth limits of residual networks commute at initialization when residual branches are scaled by $1/\sqrt{depth}$. In particular, the network output converges to the same limit whether wid…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv stat.ML
Width and Depth Limits Commute During Training