conftrace_

adaptive weight shrink

1 paper

Explore in graph

Also known as

AWS

Co-occurring keywords · papers mentioning both

deep network training (1) learning rate modulation (1) weight normalization (1) training stability (1) weight decay (1) learning rate (1) regularization theory (1) gradient descent (1) neural network optimization (1)

Papers

Understanding the Disharmony between Weight Normalization Family and Weight Decay AAAI 2020