For fixed-depth mean-field Bayesian nets on the Boolean cube, poly-sample learnability at infinite width equals poly-width learnability equals poly-bounded reduced entropy.
On the sample complexity of two-layer networks: Lipschitz vs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
For fixed-depth mean-field Bayesian nets on the Boolean cube, poly-sample learnability at infinite width equals poly-width learnability equals poly-bounded reduced entropy.