Grokking through the Lens of Minimum-Norm Interpolation
Grokking shows that fitting the training data and learning the underlying signal can occur at very different stages. However, existing theories offer limited quantitative insight into how this delayed generalization depends on inductive bias and signal structure. Our work addresses the gap by developing a statistical t...
Gil Kur, Ileana Rugina, C. Dominé et al.
· 0 citations