The minimum-weight cost of deep linear ResNets interpolates between nuclear norm and rank as the weight-decay ratio varies, implying a low bottleneck-rank bias for deep nonlinear ResNets.
The relation between the unitary representations of the complex unimodular group and its unitary subgroup
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the inductive bias of infinite-depth ResNets and the bottleneck rank
The minimum-weight cost of deep linear ResNets interpolates between nuclear norm and rank as the weight-decay ratio varies, implying a low bottleneck-rank bias for deep nonlinear ResNets.