Tube-volume bounds for smooth Pfaffian hypersurfaces yield condition-number tails for Pfaffian neural classifiers, with polynomial-in-width control for single-layer rational-weight sigmoids.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Strategic behavior can make VC-1 classes unlearnable, but first-order definability over R_exp preserves PAC learnability with complexity controlled by formula size.
citing papers explorer
-
Tubular Neighbourhoods of Pfaffian Sets and Applications to Neural Networks
Tube-volume bounds for smooth Pfaffian hypersurfaces yield condition-number tails for Pfaffian neural classifiers, with polynomial-in-width control for single-layer rational-weight sigmoids.
-
Strategic PAC Learnability via Geometric Definability
Strategic behavior can make VC-1 classes unlearnable, but first-order definability over R_exp preserves PAC learnability with complexity controlled by formula size.