conftrace_

weight dynamics

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

law of large number (1) kernel methods (1) neural network (1) gradient explosion (1) effective learning rate (1) critical learning rate (1) elr ratios (1) trainability (1) central limit theorem (1) stochastic gradient descent (1)

Papers

Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case JMLR 2024 On the Weight Dynamics of Deep Normalized Networks ICML 2024