Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks

arXiv:2605.10395 · stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.IT, cs.LG, math.IT · Submitted 2026-05-11 · Read on arXiv

stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.IT, cs.LG, math.IT

Submitted: 2026-05-11

Updated: 2026-11-17

Code: https://github.com/Minh-Toan/scaling-laws

Terminology

Sources

Related papers