Neural scaling occurs because larger models maintain learning on weaker eigenmodes of the eNTK that smaller models cannot access.
Tomasini, Alessandro Favero, and Matthieu Wyart
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
U-turn chains are Markov chains formed by short forward-backward diffusion steps that remain on the learned manifold and, with Metropolis-Hastings, sample from energy-modified targets, exhibiting an ergodicity-breaking transition on fragmented manifolds.
citing papers explorer
-
Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
Neural scaling occurs because larger models maintain learning on weaker eigenmodes of the eNTK that smaller models cannot access.
-
Sampling Data with Chains of Forward-Backward Diffusion Steps
U-turn chains are Markov chains formed by short forward-backward diffusion steps that remain on the learned manifold and, with Metropolis-Hastings, sample from energy-modified targets, exhibiting an ergodicity-breaking transition on fragmented manifolds.