A stochastic-geometric model of solution-space topology under Adam derives explicit scaling laws for grokking transition time as a function of learning rate, batch size, and L2 coefficient.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Stochastic--Geometric Theory of Scaling Laws in Grokking
A stochastic-geometric model of solution-space topology under Adam derives explicit scaling laws for grokking transition time as a function of learning rate, batch size, and L2 coefficient.