Grokking delay arises from attention performing delayed Bayesian inference over task structure after MLP memorization drives loss to zero; a KL structural intervention bypasses the inverse-weight-decay scaling.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
citing papers explorer
-
Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
Grokking delay arises from attention performing delayed Bayesian inference over task structure after MLP memorization drives loss to zero; a KL structural intervention bypasses the inverse-weight-decay scaling.
- Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization