search

jeffminlin / vmcnet

Flexible, general-purpose VMC framework, built on JAX.
https://jeffminlin.github.io/vmcnet/
MIT License
24 stars 2 forks source link

constrain norm after learning rate scaling #147

Closed nilin closed 10 months ago

nilin commented 10 months ago

that way constrain_norm doesn't need to know the learning rate

ggoldsh commented 10 months ago

Actually I have a question about this. Will this result in the "prev_grad" in the next iteration being the grad BEFORE the scaling or AFTER the scaling? I guess it depends on whether it's saved in .update() or.apply_updates().

Can you check on this to make sure it's doing the right thing before merging?