Co-occurring keywords · papers mentioning both
Papers
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
ICML 2024
Penalising the biases in norm regularisation enforces sparsity
NeurIPS 2023
A Gradient Flow Framework For Analyzing Network Pruning
ICLR 2021
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent
EMNLP 2021