Does this framework also explain grokking phenomenon?
I haven't yet fully understood your hypothesis except that behaviour gradient is useful for measuring something related to inductive bias, but above paper seems to touch a similar topic (generalization) with similar methods (experiments on fully known toy examples such as SO5).
I'm pretty sure my framework doesn't apply to grokking. I usually think about training as ending once we hit zero training loss, whereas grokking happens much later.
Does this framework also explain grokking phenomenon?
I haven't yet fully understood your hypothesis except that behaviour gradient is useful for measuring something related to inductive bias, but above paper seems to touch a similar topic (generalization) with similar methods (experiments on fully known toy examples such as SO5).