universality-classes

Tag

Cards List
#universality-classes

Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos

arXiv cs.LG ↗ · 2026-05-22 Cached

This paper develops a mean-field theory of dropout as a perturbation at the edge of chaos in neural networks, deriving scaling laws for correlation decay and establishing distinct universality classes for smooth and ReLU-like activations. It also yields optimal dropout scheduling that reduces test loss with no extra computational cost.

0 favorites 0 likes
← Back to home

Submit Feedback