2000 character limit reached
How to explain grokking (2412.18624v3)
Published 17 Dec 2024 in cond-mat.stat-mech and cs.LG
Abstract: Explanation of grokking (delayed generalization) in learning is given by modeling grokking by the stochastic gradient Langevin dynamics (Brownian motion) and applying the ideas of thermodynamics.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.