Grokked and steadily trained models learn the same features, but steady training can produce much more compressible models in a parameter regime that grokking does not reach.
Fisher information and natural gradient learning in random deep networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Grokking vs. Learning: Same Features, Different Encodings
Grokked and steadily trained models learn the same features, but steady training can produce much more compressible models in a parameter regime that grokking does not reach.