← Search

Hyunmo Kang

2 accepted papers

2025

Learning curves theory for hierarchically compositional data with power-law distributed features

ICML 2025poster

Recent theories suggest that Neural Scaling Laws arise whenever the task is linearly decomposed into units that are power-law distributed. Alternatively, scaling laws also emerge when data exhibit a hierarchically compositional structure, as is thought to occur in language and images. To unify these…

Cited by 1SourcePDFScholar