Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Deep networks learn to parse uniform-depth context-free languages from local statistics
Jack T. Parley, Francesco Cagnetta, Matthieu Wyart
Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal repres…
stat.ML2025
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta +2
Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a co…
stat.ML2025
Learning curves theory for hierarchically compositional data with power-law distributed features
Francesco Cagnetta, Hyunmo Kang, Matthieu Wyart
Recent theories suggest that Neural Scaling Laws arise whenever the task is linearly decomposed into power-law distributed units. Alternatively, scaling laws also emerge when data…