Randomly initialized depth-2 discrete networks are a priori biased toward Boolean functions with small disjunctive normal form complexity, and this bias quantitatively predicts training and generalization behavior including weight-decay effects.
Note that we do not study k-sparse functions in the main text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Characterising the Inductive Biases of Neural Networks on Boolean Data
Randomly initialized depth-2 discrete networks are a priori biased toward Boolean functions with small disjunctive normal form complexity, and this bias quantitatively predicts training and generalization behavior including weight-decay effects.