Finite-width shift of the edge of chaos in deep neural networks
Deep neural networks train best when they are initialised at the edge of chaos, the critical line in the plane of weight and bias variances on which the distance between two inputs neither grows nor shrinks with depth.
By Arn CaesararXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Nov 5, 2026.
Comments
Sign in to join the discussion.