Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

Alethea Power Yuri Burda Harrison Edwards Igor Babuschkin Vedant Misra

Published in: CoRR (2022)

Keyphrases

decision trees
case study
small number
benchmark datasets
uci machine learning repository
training error
data sets
web services
training data
preprocessing
evolutionary algorithm
dimensionality reduction
text classification
cross validation
generalization error