A predator-prey two-agent optimizer accelerates the post-memorization grokking phase by tens to a hundred times in gradient calls on modular arithmetic and MNIST, but still requires standard pre-training to memorization.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Predator-Prey Model: Driven Hunt for Accelerated Grokking
A predator-prey two-agent optimizer accelerates the post-memorization grokking phase by tens to a hundred times in gradient calls on modular arithmetic and MNIST, but still requires standard pre-training to memorization.