Know a great AI tool or AI news source? Submit it to AiByts
2 min read

Width and Depth Limits Commute During Training

Recent work established that the infinite-width and infinite-depth limits of residual networks commute at initialization when residual branches are scaled by $1/\sqrt{depth}$.

By Ruijia Zhang, Soufiane HayouarXiv - stat.ML

Read the full story

Originally published by arXiv - stat.ML on Oct 23, 2026.

Read on arXiv - stat.ML(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.