Brian Lu

Why does JoinFn use Formulas.lambdaApply instead of Formulas.betaReduce?

3

Hi! I'm attempting to write a CCG grammar using SEMPRE and I observed that the result `formula` produced by joining a binary and a unary with `JoinFn` is not fully...

Scaling the hessian by learning rate

7

Thank you for releasing the code! I'm trying to apply this method to train language models where I partition the parameters and setup a bilevel problem where the outer parameters...