cond-mat.dis-nn · 2026-11-05 · No. 164
Disordered Systems and Neural Networks, 2026-11-05.
1 new papers in cond-mat.dis-nn. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
Finite-width shift of the edge of chaos in deep neural networks
Arn Caesar
cond-mat.dis-nn · cs.LG · stat.ML
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. The line is known for infinitely wide networks; at finite width it moves, and how it moves has been disputed. We treat the logarithm of the distance between two inputs through a network of width $N$ as a random walk and compute...
This edition is part of The Daily Abstract — cond-mat.dis-nn archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.