On hierarchical grammar data with Zipf-distributed production rules, classification error decays as P^{-a/(1+a)} while next-token prediction retains a hierarchy-only asymptotic exponent.
A dynamical model of neural scaling laws
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning curves theory for hierarchically compositional data with power-law distributed features
On hierarchical grammar data with Zipf-distributed production rules, classification error decays as P^{-a/(1+a)} while next-token prediction retains a hierarchy-only asymptotic exponent.