This is a hand-designed optimizer. By definition, learned optimizer researchers would rather we learn an optimizer than hand-design one.

Learned optimizers are probably the future, but the compute budget required to create one is prohibitive.

I think learned optimizers have potential but this is disappointing. Nothing revolutionary in there…there are already sign based optimizers and this is just a slightly different take. I see learned optimizers as the possibility of getting unintuitive results but this just could have been thrown together by some grad student. Random but not surprising.